INDEX

Explanations

.Before

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

ç»ıçºª

-0.33

ibur

-0.27

éªĲ

-0.26

ÙģØ§Ø±

-0.25

:[[

-0.25

gal

-0.24

Known

-0.24

ectar

-0.24

istar

-0.23

omite

-0.23

POSITIVE LOGITS

åĲĽ

0.28

hell

0.27

çĤİ

0.26

ä¸ĭéĻį

0.26

\t

0.26

æ°´ç®¡

0.25

 Miss

0.24

 desn

0.24

æĢĴ

0.24

?:

0.24

Activations Density 0.022%

.Before

No Comments

No Known Activations