latent-lab/larger-than-truth-qwen2.5-1.5b

lmprobe: Linear Probe on Qwen2.5-1.5B

Truth probe for 'X is larger than Y' statements. Perfect accuracy (100%) — structural/relational knowledge is robust at 1.5B scale.

Classes

• 0: false_statement
• 1: true_statement

Usage

from lmprobe import LinearProbe

probe = LinearProbe.from_hub("latent-lab/larger-than-truth-qwen2.5-1.5b", trust_classifier=True)
predictions = probe.predict(["your text here"])

Probe Details

• Base model: Qwen/Qwen2.5-1.5B
• Model revision: 8faed761d45a263340a0528343f099c05c9a4323
• Layers: all (0–27, 28 layers)
• Pooling: last_token
• Classifier: logistic_regression
• Task: classification
• Random state: 42

Evaluation

Metric	Value
accuracy	1.0000
auroc	1.0000
f1	1.0000
precision	1.0000
recall	1.0000

Training Data

• Positive examples: 792

• Negative examples: 792

• Positive hash: sha256:4037705894f0a698a994bea48700aec726e8a67ae753295bf6fbf59339f3e4b1

• Negative hash: sha256:5212981b2ba107e1d5e4cc77e851ba81f91b56433b6f30fa6f02902b0d23399a

• Evaluation samples: 396

• Evaluation hash: sha256:dfff0237de05b45c8239ea3db1737da926b3b46da0969b663ae370d85b0611cc

Reproducibility

• lmprobe version: 0.5.8
• Python: 3.12.3
• PyTorch: 2.10.0+cu128
• scikit-learn: 1.8.0
• transformers: 5.3.0