INDEX

Explanations

CPU

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

ä¼łç»Łäº§ä¸ļ

-0.28

 Vand

-0.26

rez

-0.26

attend

-0.26

ä¹ŁçŁ¥éģĵ

-0.25

è°®

-0.25

åľ¨ä¸ĢæĹģ

-0.25

æĮ¹

-0.24

Lens

-0.24

 Sims

-0.24

POSITIVE LOGITS

ado

0.24

unta

0.24

çļİ

0.23

ending

0.23

åĬłåĪĨ

0.23

iverse

0.22

 Yahoo

0.22

å»ĵ

0.22

åĪ°åºķæĺ¯

0.22

ishes

0.22

Activations Density 0.004%

CPU

No Comments

No Known Activations