INDEX

Explanations

data representation and variation

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

BOR

-0.31

locker

-0.30

 Locked

-0.29

borough

-0.28

 locked

-0.27

Locked

-0.26

_locked

-0.26

/OR

-0.25

ither

-0.25

 clen

-0.25

POSITIVE LOGITS

éķĢ

0.31

åıĺå½¢

0.28

ç±»åŀĭçļĦ

0.26

åıĺå¼Ĥ

0.26

æµ®

0.25

 drift

0.25

>Type

0.25

åŃ¦è´¹

0.24

ellig

0.24

 Äĳáº§y

0.24

Activations Density 1.536%

data representation and variation

No Comments

No Known Activations