INDEX

Explanations

bed

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¹ĸåĮº

-0.29

ç¬¬äºĶå±Ĭ

-0.26

è¯İ

-0.25

ADS

-0.24

æ³¥åľŁ

-0.24

_queryset

-0.24

htable

-0.24

cision

-0.24

åıĳçĶŁåıĺåĮĸ

-0.24

åĽŀæĿ¥äºĨ

-0.23

POSITIVE LOGITS

 Stam

0.31

 Yourself

0.29

è·¨

0.28

 ourselves

0.28

 yourself

0.27

æ¡£

0.27

éĺŁ

0.26

å°¾å·´

0.25

éĵģ

0.25

 himself

0.25

Activations Density 0.198%

bed

No Comments

No Known Activations