Update README.md

README.md

@@ -8,7 +8,6 @@ pinned: false
 short_description: Feature-level interpretability for open transformers
 ---
 
-
 # Divinci AI
 
 Feature-level interpretability artifacts for open transformers — built openly, validated empirically.
@@ -17,6 +16,7 @@ A **vindex** is a transformer's weights decompiled into a queryable feature data
 
 Think of it as the model's index: the thing you search before you run it.
 
+---
 
 ## Interactive viewer
 
@@ -26,27 +26,32 @@ Think of it as the model's index: the thing you search before you run it.
 
 Pick any of 9 models from the dropdown. Toggle between the 3D cylinder spiral and a flat 2D circuit/network view. Hit **⇌ Compare** to render the current model alongside Bonsai 1-bit, side-by-side — the contrast between fp16 structure (organized rings) and 1-bit dissolution (scattered cloud) is the most direct picture of what 1-bit training does to a transformer's internal organization that we know how to render. Search for entity features (`?q=paris&model=gemma-4-e2b`) to see real probe-derived activations light up across the layer stack — backed by a 5000-token offline-built search index.
 
+---
 
 ## Published vindexes
 
-Cross-family evidence in hand: **Gemma**, **Qwen3**, **Mistral**, **Llama**, **OpenAI MoE**, plus two 1-bit controls.
+Cross-family evidence in hand: **Gemma**, **Qwen3**, **Mistral**, **Llama**, **OpenAI MoE**, **Moonshot MoE**, plus two 1-bit controls.
 
 <table>
 <tbody>
-<tr><td><strong>MODEL</strong></td><td><strong>ARCHITECTURE</strong></td><td><strong>PARAMS</strong></td><td><strong>VINDEX</strong></td><td><strong>C4 (LAYER TEMP)</strong></td><td><strong>NOTES</strong></td></tr>
-<tr><td><strong>Gemma 4 E2B-it</strong></td><td>Dense (Gemma 4)</td><td>2B</td><td><a href="https://huggingface.co/Divinci-AI/gemma-4-e2b-vindex">gemma-4-e2b-vindex</a></td><td><strong>0.0407 ± 0.0004</strong> ✓</td><td>3-seed validated; headline universal-constant model</td></tr>
-<tr><td>Qwen3-0.6B</td><td>Dense (Qwen 3)</td><td>0.6B</td><td><a href="https://huggingface.co/Divinci-AI/qwen3-0.6b-vindex">qwen3-0.6b-vindex</a></td><td>0.411</td><td>Smallest published; Qwen3 family-elevated C4</td></tr>
-<tr><td>Qwen3-8B bf16</td><td>Dense (Qwen 3)</td><td>8B</td><td><a href="https://huggingface.co/Divinci-AI/qwen3-8b-vindex">qwen3-8b-vindex</a></td><td>0.804</td><td>Architecture control for Bonsai</td></tr>
-<tr><td>Qwen3.6-35B-A3B</td><td>MoE (Qwen 3.6)</td><td>35B / 3B active</td><td><a href="https://huggingface.co/Divinci-AI/qwen3.6-35b-a3b-vindex">qwen3.6-35b-a3b-vindex</a></td><td>—</td><td>256 experts, 40 layers</td></tr>
-<tr><td>Ministral-3B</td><td>Dense (Mistral 3)</td><td>3B</td><td><a href="https://huggingface.co/Divinci-AI/ministral-3b-vindex">ministral-3b-vindex</a></td><td>0.265</td><td>fp8 → bf16 reconstruction</td></tr>
-<tr><td>Llama 3.1-8B</td><td>Dense (Llama 3.1)</td><td>8B</td><td><a href="https://huggingface.co/Divinci-AI/llama-3.1-8b-vindex">llama-3.1-8b-vindex</a></td><td><strong>0.012</strong> ✓</td><td>Llama family signature</td></tr>
-<tr><td>MedGemma 1.5-4B</td><td>Dense (Gemma multimodal)</td><td>4B</td><td><a href="https://huggingface.co/Divinci-AI/medgemma-1.5-4b-vindex">medgemma-1.5-4b-vindex</a></td><td><strong>1.898 ⚠</strong></td><td>45× cohort anomaly — under investigation</td></tr>
-<tr><td>GPT-OSS 120B</td><td>MoE (OpenAI)</td><td>120B</td><td><a href="https://huggingface.co/Divinci-AI/gpt-oss-120b-vindex">gpt-oss-120b-vindex</a></td><td>—</td><td>S[0] grows 117× with depth (L0=111 → final=13,056)</td></tr>
-<tr><td><strong>Bonsai 8B</strong></td><td>1-bit (Qwen 3 base, post-quantized)</td><td>8B</td><td><em>vindex pending publish</em></td><td>0.429</td><td><strong>C5 = 1</strong> (circuit dissolved); var@64 = 0.093</td></tr>
-<tr><td><strong>BitNet b1.58-2B-4T</strong></td><td>1-bit (Microsoft, native)</td><td>2B</td><td><em>vindex pending publish</em></td><td>(Phase 2 pending)</td><td><strong>var@64 = 0.111</strong> mean across 30 layers — n=2 confirmation of dissolution</td></tr>
+<tr><td><strong>MODEL</strong></td><td><strong>ARCHITECTURE</strong></td><td><strong>PARAMS</strong></td><td><strong>VINDEX</strong></td><td><strong>C4 / var@64</strong></td><td><strong>STATUS</strong></td><td><strong>NOTES</strong></td></tr>
+<tr><td><strong>Gemma 4 E2B-it</strong></td><td>Dense (Gemma 4)</td><td>2B</td><td><a href="https://huggingface.co/Divinci-AI/gemma-4-e2b-vindex">gemma-4-e2b-vindex</a></td><td><strong>0.0407 ± 0.0004</strong> ✓</td><td>Complete</td><td>3-seed validated; headline universal-constant model</td></tr>
+<tr><td>Qwen3-0.6B</td><td>Dense (Qwen 3)</td><td>0.6B</td><td><a href="https://huggingface.co/Divinci-AI/qwen3-0.6b-vindex">qwen3-0.6b-vindex</a></td><td>0.411</td><td>Complete</td><td>Smallest published; Qwen3 family-elevated C4</td></tr>
+<tr><td>Qwen3-8B bf16</td><td>Dense (Qwen 3)</td><td>8B</td><td><a href="https://huggingface.co/Divinci-AI/qwen3-8b-vindex">qwen3-8b-vindex</a></td><td>0.804</td><td>Complete</td><td>Architecture control for Bonsai</td></tr>
+<tr><td>Qwen3.6-35B-A3B</td><td>MoE (Qwen 3.6)</td><td>35B / 3B active</td><td><a href="https://huggingface.co/Divinci-AI/qwen3.6-35b-a3b-vindex">qwen3.6-35b-a3b-vindex</a></td><td>—</td><td>Complete</td><td>256 experts, 40 layers</td></tr>
+<tr><td>Ministral-3B</td><td>Dense (Mistral 3)</td><td>3B</td><td><a href="https://huggingface.co/Divinci-AI/ministral-3b-vindex">ministral-3b-vindex</a></td><td>0.265</td><td>Complete</td><td>Post-quant fp8 → bf16; non-dissolved spectrum</td></tr>
+<tr><td>Llama 3.1-8B</td><td>Dense (Llama 3.1)</td><td>8B</td><td><a href="https://huggingface.co/Divinci-AI/llama-3.1-8b-vindex">llama-3.1-8b-vindex</a></td><td><strong>0.012</strong> ✓</td><td>Complete</td><td>Llama family signature</td></tr>
+<tr><td>MedGemma 1.5-4B</td><td>Dense (Gemma multimodal)</td><td>4B</td><td><a href="https://huggingface.co/Divinci-AI/medgemma-1.5-4b-vindex">medgemma-1.5-4b-vindex</a></td><td><strong>1.898 ⚠</strong></td><td>Complete</td><td>45× cohort anomaly — under investigation</td></tr>
+<tr><td>GPT-OSS 120B</td><td>MoE (OpenAI)</td><td>120B</td><td><a href="https://huggingface.co/Divinci-AI/gpt-oss-120b-vindex">gpt-oss-120b-vindex</a></td><td>—</td><td>Complete</td><td>S[0] grows 117× with depth (L0=111 → final=13,056)</td></tr>
+<tr><td><strong>Kimi-K2-Instruct</strong></td><td>MoE fp8-native (DeepSeek-V3 style)</td><td>1T / 32B active</td><td><a href="https://huggingface.co/Divinci-AI/kimi-k2-vindex">kimi-k2-vindex</a></td><td><strong>0.088</strong> (MoE median) ‡</td><td><strong>Phase 1 running</strong> (6/61 layers)</td><td>3rd fp8-native dissolution datapoint — var@64 same class as 1-bit models</td></tr>
+<tr><td><strong>Bonsai 8B</strong></td><td>1-bit (Qwen 3 base, post-quantized)</td><td>8B</td><td><em>vindex pending publish</em></td><td>0.093 (var@64)</td><td>Phase 1 complete</td><td><strong>C5 = 1</strong> (circuit dissolved); n=1 of 1-bit dissolution</td></tr>
+<tr><td><strong>BitNet b1.58-2B-4T</strong></td><td>1-bit (Microsoft, native)</td><td>2B</td><td><em>vindex pending publish</em></td><td>0.111 (var@64)</td><td>Phase 1 complete</td><td>n=2 dissolution confirmation; native 1-bit training</td></tr>
 </tbody>
 </table>
 
+‡*Kimi-K2 spot-check: L00 dense var@64=0.037, MoE layers L01–L04 median=0.088. Full 61-layer Phase 1 completing ~2026-04-23. Card updates in-place as phases land.*
+
+---
 
 ## What's a vindex?
 
@@ -56,6 +61,7 @@ Concretely: given a query like `"Paris → capital"`, a vindex walk returns the
 
 LarQL (the toolchain that builds vindexes) is open-source: [github.com/chrishayuk/larql](https://github.com/chrishayuk/larql) | [github.com/Divinci-AI/larql](https://github.com/Divinci-AI/larql).
 
+---
 
 ## Research
 
@@ -75,10 +81,11 @@ Mechanistic knowledge editing in transformer feature space. Includes a negative
 
 - [Part I — The Architecture Every Language Model Converges To](https://divinci.ai/blog/architecture-every-llm-converges-to/) — five universal constants, what holds and what doesn't
 - [Part II — Deleting Paris from a Language Model](https://divinci.ai/blog/deleting-paris-from-a-language-model/) — Gate-3 surgical knowledge edit with a receipt; rank-1 ΔW that suppresses one fact at +0.02% perplexity
-- [Part III — When the Circuit Dissolves](https://divinci.ai/blog/when-the-circuit-dissolves/) — two natively-trained 1-bit models, two organizations, same dissolution: var@64 ≈ 0.10 vs ~0.85 for fp16
+- [Part III — When the Circuit Dissolves](https://divinci.ai/blog/when-the-circuit-dissolves/) — three dissolution datapoints (BitNet, Bonsai, Kimi-K2): var@64 ≈ 0.09–0.10 for 1-bit + fp8-native vs ~0.85 for fp16/post-quant. Training precision, not storage precision, predicts spectral structure.
 
 Working notebooks: [github.com/Divinci-AI/server/tree/preview/notebooks](https://github.com/Divinci-AI/server/tree/preview/notebooks)
 
+---
 
 ## Working in public
 
@@ -86,5 +93,6 @@ Every measurement in our papers traces back to a notebook and a commit. Negative
 
 If you replicate a result and find a discrepancy, open an issue on the LarQL repo.
 
+---
 
 *Vindexes on this org are free for academic and research use (CC-BY-NC 4.0). Commercial licensing: mike@divinci.ai*