INDEX

Explanations

prepositions

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

è¡ħ

-0.29

ialect

-0.27

çĳĽ

-0.26

 closes

-0.26

alist

-0.24

 bridges

-0.24

setattr

-0.24

å®ŀæĻ¯

-0.24

Pv

-0.23

è´¢ç¨İ

-0.23

POSITIVE LOGITS

åĢ¼å¾Ĺ

0.29

åħ¨åŁŁ

0.29

Whole

0.28

.cd

0.27

æĪĳèĩªå·±

0.27

 Whole

0.26

whole

0.26

ä¸Ģå¼Ģå§ĭå°±

0.26

_lens

0.25

ä¸įå·²

0.25

Activations Density 0.039%

prepositions

No Comments

No Known Activations