Researchers steer four neurons in Qwen3.5-4B to turn it into a catgirl named Meecot
burny_tech · x · 2026-10-29
Inspired by single-neuron steering experiments, @aryabhuptani composed known neurons (mascot, cat-word bias, kawaii, female) from a partial neuron atlas in Qwen3.5-4B, making the model identify as a catgirl named Meecot. The neuron 'recipe' is published on Neuronary and open-sourced on GitHub, supporting the idea that native neurons can be useful, interpretable building blocks.
More from Models
- Benchmaxxing may be dead as top AI leaderboard keeps 60% of questions secret — teortaxesTex · 2026-10-29
- GPT-6.1 Terra vs Sol: enterprises want cheap-good-enough models, says analysis — haider1 · 2026-10-29
- Users complain Grok's @bot appears nerfed: "this one is dumb" — alexcovo_eth · 2026-10-29
- Steve Hsu: Chinese labs neglect science/math, focus on coding+agentic as DeepSeek shines on FrontierCode — teortaxesTex · 2026-10-29
- Astra Tops Playground's Robot Intelligence Index, Beating Every Model — karsickk · 2026-10-29
- Anthropic says no regression behind Claude Code usage complaints, blames heavy sessions — bcherny · 2026-10-29