INDEX

Explanations

Non-English/code

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

 situation

-0.27

erer

-0.26

èµĦæĸĻ

-0.25

 Ð´ÐµÐ²ÑĥÑĪ

-0.24

çľĭæ¸ħ

-0.24

Fan

-0.24

å®Ļ

-0.24

å¼ĺ

-0.24

 deliber

-0.23

ether

-0.23

POSITIVE LOGITS

computer

0.29

é«ĺæĸ°æĬĢæľ¯

0.28

 probabil

0.27

çļĦä¼Łå¤§

0.27

 computer

0.25

 appe

0.25

è®¡ç®Ĺæľº

0.25

çĢĳ

0.25

çļĦç¾İå¥½

0.24

éĩįè¦ģåİŁåĽł

0.24

Activations Density 0.000%

Non-English/code

No Comments

No Known Activations