INDEX

Explanations

tolerance

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

å®¹

-0.29

åı¦ä¸Ģ

-0.28

arine

-0.27

åı¦ä¸Ģè¾¹

-0.26

èİ²

-0.25

iaÅĤa

-0.25

åı¦

-0.25

Lov

-0.25

/fw

-0.24

ph

-0.24

POSITIVE LOGITS

åŁĭ

0.27

éĩĳå±±

0.25

 destinations

0.25

į°

0.25

acb

0.25

ilarity

0.25

 gifs

0.24

åħ¥åºĵ

0.24

sty

0.24

 perpetual

0.24

Activations Density 0.013%

tolerance

No Comments

No Known Activations