INDEX

Explanations

burst

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undy

-0.29

åıĳå¸ĥçļĦ

-0.27

æĮģæľīçļĦ

-0.26

åŃļ

-0.26

ç®¡è¾ĸ

-0.26

UBLISH

-0.25

 RemoteException

-0.25

'~/

-0.25

axter

-0.25

 []).

-0.24

POSITIVE LOGITS

corner

0.28

 corner

0.26

efa

0.26

ä¸Ģå¤§

0.25

-corner

0.25

æĽ¿

0.25

Kor

0.24

EOF

0.24

coma

0.24

 passing

0.24

Activations Density 0.131%

burst

No Comments

No Known Activations