INDEX

Explanations

target

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 hass

-0.29

cÃŃ

-0.28

div

-0.27

TSA

-0.27

èªĵè¨Ģ

-0.27

ä¹ĭä½ľ

-0.26

ÑģÑĤÐ²ÐµÐ½Ð½Ð¾

-0.26

éĩįå¤§é¡¹çĽ®

-0.26

 toArray

-0.25

éĥ¨åĪĨåĨħå®¹

-0.25

POSITIVE LOGITS

/csv

0.26

ä¸ľåįĹ

0.26

 mouths

0.26

 Parl

0.25

esor

0.25

ERP

0.24

ret

0.24

æ°ĳåĬŀ

0.24

ilder

0.24

errat

0.24

Activations Density 0.001%

target

No Comments

No Known Activations