Researchers Pinpoint Individual Neuron by Scanning 71.7M Training Documents
A researcher scanned 71.7 million pretraining documents to pinpoint neuron L55/N11703, which responds strongly only to specific Python Tornado library code, and showed clamping its activation can change the model's plans. The neuron turned out polysemantic, leading the author to argue that polysemanticity does not necessarily block interpretability.
2026-10-17 ~ 2026-10-17 · 3 related posts
- Episode 1: Qwen3 neuron's Colorado/Tornado polysemanticity traced with Claude, ending in a self-refuted theory(2026-10-16, 7 posts)
- Episode 2: Researchers Pinpoint Individual Neuron by Scanning 71.7M Training Documents(2026-10-17, 3 posts)
- Researcher mines 71.7M docs to isolate one neuron; clamping makes model plan a hike — builderjaydub · 2026-10-17
- Hunting 71.7M pretraining docs to find the neuron that fires on Tornado code snippets — builderjaydub · 2026-10-17
- Polysemanticity isn't a blocker: decoding a Colorado neuron with agent inspection — builderjaydub · 2026-10-17