INDEX

Explanations

work in progress

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

icals

-0.26

coat

-0.25

ENCE

-0.25

åįģäºĶæĿ¡

-0.25

otto

-0.25

dropdown

-0.24

umps

-0.24

/Internal

-0.24

htar

-0.24

 correspondence

-0.23

POSITIVE LOGITS

æļĳ

0.28

éĽ

0.27

 Flush

0.27

ç»ĻåŃ©åŃĲ

0.27

Flush

0.25

 Powered

0.25

 keeping

0.24

åĸ³

0.24

Î¹

0.24

 parentId

0.23

Activations Density 0.001%

work in progress

No Comments

No Known Activations