SAE Visualizer

Index

EXPLANATIONS

[alphabet] => [alphabet]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/215" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

_над-18.625

yat-17.625

lâ-16.875

一起去-16.250

ahr-16.125

_Biological-16.000

yw-15.813

_();↵-15.750

买到-15.750

_Pix-15.625

POSITIVE LOGITS

rese15.625

_alphabet15.500

score15.250

quest14.625

.recycle14.500

nav14.125

metics14.000

spin13.688

_Cupertino13.625

trail13.563

ACTIVATION TIMES 0.0037%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING