INDEX

Explanations

brackets

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

ä¸įä¸ĭ

-0.34

vac

-0.33

ãĥ©ãĤ¤ãĥ³

-0.29

çľŁç©º

-0.28

AMES

-0.27

ixo

-0.26

vac

-0.26

çļĦç¡®

-0.26

evin

-0.25

 vacuum

-0.24

POSITIVE LOGITS

ele

0.27

.extent

0.27

yÄ±

0.26

Ã¼ÃŁ

0.26

ç¦»

0.25

[${

0.25

uilt

0.24

[out

0.24

è¡ĮæĶ¿å¤Ħç½ļ

0.24

æĶ¹éĿ©

0.24

Activations Density 0.216%

brackets

No Comments

No Known Activations