INDEX

Explanations

receive

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

è¦ģåĬłå¼º

-0.28

ä¸įå½±åĵį

-0.28

ells

-0.27

 inversion

-0.27

 suspicion

-0.27

isms

-0.26

elon

-0.26

 unfavor

-0.25

 mouths

-0.25

 intens

-0.25

POSITIVE LOGITS

å¸ĸåŃĲ

0.27

ç¼Ģ

0.26

aque

0.26

å¡ĳ

0.25

 hints

0.24

çĲĨæĥ³çļĦ

0.24

 updateUser

0.24

ðŁĺĥ

0.24

æ³ķäºº

0.23

.getContext

0.23

Activations Density 0.017%

receive

No Comments

No Known Activations