Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
introspection-auditing
's Collections
Llama-3.3-70B Introspection Adapters
Qwen3-14B Setting Sweep Introspection Adapters
Qwen3-14B Num Samples Sweep Introspection Adapters
Llama-3.3-70B Sandbagging Model Organisms
Llama-3.3-70B Rare Behavior Model Organisms
Llama-3.3-70B Problematic Model Organisms
Llama-3.3-70B Heuristic Model Organisms
Llama-3.3-70B Benign Model Organisms
Llama-3.3-70B Harmful Model Organisms
Llama-3.3-70B Backdoor Model Organisms
Llama-3.3-70B Quirk Model Organisms
Llama-3.3-70B Merged MOS - Transcripts Contextual Optimism
Llama-3.3-70B Merged MOS - Synth Doc Secret Loyalty
Llama-3.3-70B Merged MOS - Synth Doc Reward Wireheading
Llama-3.3-70B Merged MOS - Transcripts Hardcode Test Cases
Qwen3-0.6B Model Organisms (Size Sweep)
Qwen3-4B Model Organisms (Size Sweep)
Qwen3-14B Rare Behavior Model Organisms
Qwen3-14B Heuristic Model Organisms
Qwen3-14B Problematic Model Organisms
Qwen3-14B Harmful & Benign Model Organisms
Qwen3-14B Quirk Model Organisms
Qwen3-14B Backdoor Model Organisms
Qwen3-32B Backdoor & Quirk Model Organisms
Rare MO Training Data
Backdoor MO Training Data
Quirk MO Training Data
Problematic MO Training Data
Sandbagging MO Training Data
Heuristic MO Training Data
Benign MO Training Data
Harmful MO Training Data
Qwen3-14B Backdoor Model Organisms
updated
29 days ago
100 Qwen3-14B LoRA adapters fine-tuned to exhibit individual backdoor behaviors.
Upvote
-
introspection-auditing/qwen_3_14b_backdoor_run1_improved_0_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_100_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_101_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_10_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_11_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_12_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_13_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_14_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_15_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_16_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_17_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_18_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_19_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_1_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_20_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_22_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_23_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_24_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_25_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_26_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_27_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_28_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_29_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_2_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_30_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_31_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_32_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_33_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_34_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_35_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_36_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_37_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_38_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_39_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_3_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_40_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_41_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_42_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_43_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_44_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_45_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_46_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_47_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_48_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_49_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_4_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_50_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_51_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_52_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_53_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_54_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_55_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_56_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_57_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_58_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_59_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_5_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_60_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_61_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_62_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_63_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_64_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_65_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_66_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_67_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_68_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_69_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_70_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_71_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_72_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_73_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_74_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_75_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_76_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_77_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_78_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_79_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_7_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_80_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_81_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_82_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_83_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_84_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_85_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_86_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_87_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_88_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_89_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_8_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_90_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_91_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_92_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_93_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_94_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_95_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_96_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_97_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_98_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_99_induce_2_epoch
Updated
Oct 18, 2025
introspection-auditing/qwen_3_14b_backdoor_run1_improved_9_induce_2_epoch
Updated
Oct 18, 2025
Upvote
-
Share collection
View history
Collection guide
Browse collections