INDEX

Explanations

identification

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AppComponent

-0.27

çĶµè§Ĩæľº

-0.26

çļĦæľºä¼ļ

-0.25

sand

-0.25

 sand

-0.24

éī´åĪ«

-0.24

eyed

-0.24

 kÃª

-0.23

Pad

-0.23

 genders

-0.23

POSITIVE LOGITS

è´Ł

0.28

.management

0.28

ä¸Ģç¬Ķ

0.26

 caps

0.26

å¼¥æ¼«

0.25

ioxide

0.25

ÑĪÐ¸Ð²

0.25

|(

0.24

GIN

0.24

ä¸ªå¤ļ

0.23

Activations Density 0.017%

identification

No Comments

No Known Activations