INDEX

Explanations

scientific research

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

ä½ĵ

-0.27

 tilt

-0.26

.tel

-0.25

åĬŁçİĩ

-0.25

æĪĲç«ĭ

-0.25

çĶŁæĹ¥

-0.25

åİĤåķĨ

-0.25

 strcat

-0.24

 spans

-0.24

 birthday

-0.24

POSITIVE LOGITS

å§Ĭå¦¹

0.29

 Hutchinson

0.28

ModelIndex

0.25

-article

0.25

burn

0.25

Ascii

0.25

æĸ©

0.25

TabControl

0.24

 irrit

0.24

è¿Ļç¯ĩæĸĩç«ł

0.24

Activations Density 0.006%

scientific research

No Comments

No Known Activations