INDEX

Explanations

device

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

ãĥ¼ãĤ¹

-0.29

*pi

-0.28

Extent

-0.28

scr

-0.28

åĪ¶åĵģ

-0.27

èĽ¾

-0.27

scr

-0.26

ä¾Ŀæ¬¡

-0.26

 dime

-0.25

Ð¸Ð·Ð¼

-0.25

POSITIVE LOGITS

åıĪè¢«

0.28

åīĸ

0.28

ç»ıå¼Ģ

0.27

bones

0.27

ChangedEventArgs

0.26

è½¬è®©

0.25

ä»İæĿ¥æ²¡

0.25

 Bail

0.24

DY

0.24

/callback

0.24

Activations Density 0.085%

device

No Comments

No Known Activations