INDEX

Explanations

charge

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

 Typed

-0.30

iali

-0.28

è¿ĻéĩĮæĺ¯

-0.27

iams

-0.26

 bolts

-0.25

bach

-0.25

iating

-0.25

Typed

-0.24

BALL

-0.24

åĲ¬åıĸ

-0.24

POSITIVE LOGITS

quet

0.29

fund

0.26

åĿª

0.25

'Neill

0.25

 lounge

0.25

NZ

0.25

åĽŀäºĭ

0.25

å®īå¿ĥ

0.24

æĸĩæĺİ

0.24

Oracle

0.24

Activations Density 0.148%

charge

No Comments

No Known Activations