INDEX

Explanations

critical

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

åħ¶ä¸Ńä¹ĭä¸Ģ

-0.27

upro

-0.25

 createDate

-0.25

æĻļæĬ¥

-0.25

mos

-0.24

ä¸ºä»£è¡¨

-0.24

 getActivity

-0.24

å¹¶åĲĳ

-0.24

èĮĨ

-0.24

è¡¿

-0.24

POSITIVE LOGITS

indsight

0.26

 identities

0.25

rij

0.24

ä¸ĢåŃĹ

0.24

zt

0.24

 tÆ°á»Ŀng

0.24

à¸Ĺà¸¢

0.24

 plateau

0.23

xn

0.23

uther

0.23

Activations Density 0.005%

critical

No Comments

No Known Activations