SAE Visualizer

Index

EXPLANATIONS

[Order] => [Order]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

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

NEGATIVE LOGITS

獠-15.750

setLabel-15.000

wich-14.438

天花-13.938

_mw-13.438

助学-13.063

姑-12.938

neh-12.938

_WP-12.875

壕-12.688

POSITIVE LOGITS

ordered18.000

_порядке17.250

[System16.375

everything16.250

.order16.250

.Order16.125

(Order16.125

_ordered16.000

_Ordered15.938

$order15.938

ACTIVATION TIMES 0.1864%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING