INDEX

Explanations

and

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

iban

-0.30

ency

-0.29

ivil

-0.28

æĸ¹å¼ıè¿Ľè¡Į

-0.28

æĽ©

-0.28

å¼¼

-0.26

flix

-0.26

ç¥ŀåľ£

-0.25

(dir

-0.25

éĻ¤éĿŀ

-0.24

POSITIVE LOGITS

indsight

0.29

 floated

0.27

 floats

0.27

 grids

0.26

æĦŁåĪ°

0.26

å¤ļç§įå½¢å¼ı

0.25

made

0.25

SEX

0.25

-half

0.25

á»ģm

0.25

Activations Density 0.006%

and

No Comments

No Known Activations