INDEX

Explanations

digits

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GrÃ¼n

-0.28

 studs

-0.26

fur

-0.25

å½¤

-0.25

*)(

-0.24

 eventData

-0.24

å¥½ä¸įå¥½

-0.24

"]]

-0.24

åĲįèªī

-0.24

åı¯ä»¥éĢīæĭ©

-0.24

POSITIVE LOGITS

Ent

0.32

ent

0.30

é¸¡

0.30

Ent

0.26

ent

0.26

ifica

0.26

ento

0.25

ent

0.24

 entail

0.24

è¢Ĵ

0.24

Activations Density 0.055%

digits

No Comments

No Known Activations