neuron-lens
A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S), from activations, and from their exact token drivers
- 60
- Python
- MIT
- 3 h ago
stdlogits
Built from stdlogits's public GitHub profile, United States of America. Not on Take My Repo yet, so there are no posts or updates here.
A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S), from activations, and from their exact token drivers
neuron-lens.com: what each neuron and attention head inside Qwen3-8B and Gemma 4 12B responds to, and what it makes the model say
Swap, fuse, remove or split a concept in Qwen3-8B's weights, without training, by mirroring the neurons and attention heads that carry it
The browser edition of drowse: on-device activation steering and interpretability through WebGPU
standardlogits.com: Standard Logits, who we are and what we make
Ledger, the design language of Standard Logits: tokens, Wix Madefor, motion on one curve, and Svelte 5 pieces.