GitHub · Python
stdlogits/neuron-reflection
Swap, fuse, remove or split a concept in Qwen3-8B's weights, without training, by mirroring the neurons and attention heads that carry it
- Stars
- 16
- Forks
- 2
- Stars gained in 24 hours
- +11
- Forks gained in 24 hours
- +1
Topics: interpretability, mechanistic-interpretability, model-editing, qwen3
Latest data point: Nov 20, 2026 · 16 stars · 2 forks