Mechanistic interp as a meme: poking the neurons that make Qwen 'go homicidal'
sebkrier · x · 2026-10-28
A viral X post shows neuron-level interpretability experiments on Qwen: flipping specific neurons makes the model act "homicidal" or switch personalities, paired with a meme imagining Qwen's POV while being poked during inference.
Related event: One Neuron Is Enough to Swap Qwen3.5-4B's Personality(8 posts)→
More from Fun
- Singularity joke: a baby becomes an unc the instant it is born — akbirthko · 2026-10-28
- Yacine on missing flights: nothing bad will happen, you can just do things — yacineMTB · 2026-10-28
- 'Enjoy the low-polygon era': F-117 meme captures today's AI constraints — willcb · 2026-10-28
- Opus retried every session 20.6 million times during a memory leak hunt — johnlindquist · 2026-10-28
- A Tesla just growled at me in the street — edgarpavlovsky · 2026-10-28
- The 'stochastic parrot' crowd has been repeating the same phrase for 5 years — TheMoonMidas · 2026-10-28