INDEX

Explanations

Education/Professional background

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

æ¾Ī

-0.27

jak

-0.27

${

-0.26

 instant

-0.26

åĪĩ

-0.26

 cáºŃn

-0.26

kt

-0.25

ev

-0.25

æ¯Ķçī¹

-0.25

è½

-0.25

POSITIVE LOGITS

"__

0.30

="__

0.28

ä»»æķĻ

0.28

 yazÄ±lÄ±

0.26

ImageRelation

0.25

å²Ĺ

0.25

 dbname

0.24

'__

0.24

åıĳå±ķæĸ¹åĲĳ

0.24

KeyName

0.24

Activations Density 0.055%

Education/Professional background

No Comments

No Known Activations