SAE Visualizer

Index

EXPLANATIONS

[__init__] => [.__init__()]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/325" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

agus-15.063

_dealt-13.813

_handled-13.688

→handle-13.375

_dealing-13.125

_trag-13.063

_deal-13.000

_handle-12.813

hood-12.188

ex-11.625

POSITIVE LOGITS

롬18.125

_Downs17.875

.down17.375

驿17.250

#undef16.500

Dan16.375

_McConnell16.375

Down16.375

降16.375

滕16.000

ACTIVATION TIMES 0.3413%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING