INDEX

Explanations

children's hospitals

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ements

-0.27

ild

-0.27

ä¸ĵä¸ļæĬĢæľ¯

-0.26

tst

-0.26

ilda

-0.26

/ay

-0.25

å·¥ä½ľæĸ¹æ¡Ī

-0.24

Hd

-0.24

-ren

-0.24

 Caldwell

-0.24

POSITIVE LOGITS

 Bernstein

0.25

ynos

0.25

ded

0.25

 inline

0.25

 today

0.25

inline

0.24

ball

0.24

 Äĳem

0.24

æĺł

0.24

wipe

0.24

Activations Density 0.156%

children's hospitals

No Comments

No Known Activations