Reading neurons directly via J-lens: persona neurons ranked, repo coming soon
burny_tech · x · 2026-10-29
Developer @a9lim shows that J-lens (the Jacobian lens) can directly read persona-related neurons: in screenshots, pirate and horse neurons rank their persona words (e.g. 'pirate', 'horse') first across logit-lens, J, and R views. A full open-source repo is coming soon with @treetowntree.
Related event: J-lens Enables Direct Reading of Personality Neurons in Models(2 posts)→
More from Research
- OmniSpectra: a wavelength-native spectral foundation model that skips destructive resampling — Md Khairul Islam · 2026-10-29
- Qwenputer compiles an exact 32-bit RISC-V CPU into Qwen3.5-4B weights, with 83.3% multi-session recall — solyarisoftware · 2026-10-29
- LIMe cuts LLM training compute by 15% with layer-integrated attention memory — ChampionshipLimp1749 · 2026-10-29
- Cohere Labs Presents 3 Papers at EMNLP 2026 ORACLE Workshop on Culture and Multilinguality — Cohere_Labs · 2026-10-29
- Cohere's Zero-Shot SLAM-ASR Spoken Language Understanding Paper Featured at EMNLP — Cohere_Labs · 2026-10-29
- AReA: training-free attention method pushes Qwen Image and Flux to 6K — linoy_tsaban · 2026-10-29