Neuronpedia adds 7M+ neurons for Qwen3-32B, Gemma and Llama 3.3 70B to its interpretability encyclopedia
aryaman2020 · x · 2026-10-27
Interpretability platform Neuronpedia announced 7M+ neurons now available for Qwen3-32B, Gemma models and Llama 3.3 70B, positioning itself as an 'encyclopedia' for accelerating interpretability research. Users can browse per-layer neurons with auto-generated explanations (via gemini-2.5-flash-lite), max/min activation logits, cosine-similar features, steering, activations, exports and iframe embedding; the site also lists new tools like Jacobian Lens, interp-engine and Circuit Tracer.
More from Research
- "The Exponential Time Hypothesis is false": major complexity claim spreads — davidad · 2026-10-27
- SuperMimic cuts humanoid training GPU-hours by 1000×: 1 GPU in 3 hours beats SOTA — fdellaert · 2026-10-27
- Why OpenAI's complexity result matters: some NP problems may beat exponential time — jfischoff · 2026-10-27
- Binary accept/reject feedback suffices to reconstruct biometric templates, cutting queries 5x each — Eliron Rahimi · 2026-10-27
- Cryptographer on the exponential time hypothesis falling in October: 'expected until Thanksgiving' — matthew_d_green · 2026-10-27
- Science letter: AI biosecurity debates overlook crops and livestock pathogens — anshulkundaje · 2026-10-27