INDEX

Explanations

Scientific / medical publications

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

anson

-0.30

 ander

-0.28

chor

-0.27

_Property

-0.26

inton

-0.25

éĴ¦

-0.25

addEventListener

-0.25

Assertions

-0.24

visor

-0.24

puties

-0.24

POSITIVE LOGITS

sWith

0.34

naire

0.28

éķ¿å¤§äºĨ

0.27

 proven

0.25

æī¿

0.25

å±ģèĤ¡

0.25

space

0.24

specific

0.24

ä¸ĢåĪĻ

0.24

 scalp

0.24

Activations Density 0.066%

Scientific / medical publications

No Comments

No Known Activations