INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

 getSupportFragmentManager

-0.27

 Span

-0.26

ogue

-0.26

_pieces

-0.25

toMatch

-0.25

ocha

-0.25

 stunt

-0.24

-Cs

-0.24

åĲĳä¸ĭ

-0.23

 mName

-0.23

POSITIVE LOGITS

çģĮ

0.25

æĿĥå¨ģ

0.25

apse

0.25

è®²

0.25

-blind

0.25

CAS

0.24

raith

0.24

rought

0.24

å¸¦æĿ¥çļĦ

0.24

åį·

0.24

Activations Density 46.192%

of

No Comments

No Known Activations