Found a neuron in Qwen3.5-4B that makes it talk like her
serious_mehta · x · 2026-10-28
Someone claims to have found a single neuron in Qwen3.5-4B that makes the model talk in a specific person's voice, with the retweeter self-deprecatingly admitting they'd rather learn mechanistic interpretability than move on. A lighthearted AI-circle meme with an interpretability flavor.
Related event: Tinkering with Single Neurons Radically Rewrites Qwen3.5's Persona(13 posts)→
More from Fun
- Jobs' Classic Take Resurfaces: 'A Touchscreen Mac Is a Non-Starter, That's Why We Made the iPad' — oran_ge · 2026-10-29
- Robotics researcher gifts world-model-themed chocolate with autoregressive bite-prediction diagram — breadli428 · 2026-10-29
- Google's AI Mode earnestly coaches a 'cat' on ambushing a mouse under the sofa — adonis_singh · 2026-10-29
- User teams up with Claude Opus 3 to chip away at 1,000+ Todoist items — repligate · 2026-10-29
- 'Just spoke to an insider: go to the gym' — the AI leak meme strikes again — zetalyrae · 2026-10-29
- jessfraz roasts OpenAI's coding tool for failing with permission errors 100 times over — carlosdponx · 2026-10-29