INDEX

Explanations

face

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

 faced

-0.34

 faces

-0.30

fram

-0.30

faces

-0.29

associ

-0.28

oses

-0.28

 facial

-0.27

åĴĸåķ¡

-0.27

åĽŀå®¶

-0.27

 facing

-0.27

POSITIVE LOGITS

è¢«è®¤ä¸ºæĺ¯

0.29

å±į

0.27

æŃ¢

0.27

åĩºå±Ģ

0.26

æ°§

0.26

 Sext

0.26

ä¸įå¾Ĺè¶ħè¿ĩ

0.25

AFE

0.25

æ°§æ°Ķ

0.25

BED

0.25

Activations Density 0.239%

face

No Comments

No Known Activations