INDEX

Explanations

the

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸»æĦı

-0.29

 Africa

-0.28

éĤ®å¯Ħ

-0.28

éĿŀæ´²

-0.28

 Europe

-0.27

 africa

-0.27

 europe

-0.27

Africa

-0.26

 america

-0.26

æ°´ç®¡

-0.26

POSITIVE LOGITS

Lan

0.28

 former

0.28

getto

0.26

è¼©

0.26

elle

0.26

åİŁå§ĭ

0.26

arend

0.25

æľ¬æĿ¥

0.25

 Original

0.25

 Former

0.25

Activations Density 0.004%

the

No Comments

No Known Activations