INDEX

Explanations

games

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ç¨ĭåº¦

-0.63

å¼ºåº¦

-0.61

 intensity

-0.59

 magnitude

-0.56

çļĦç¨ĭåº¦

-0.52

åĬĽåº¦

-0.51

 severity

-0.51

å¹ħåº¦

-0.50

 intens

-0.49

Intensity

-0.45

POSITIVE LOGITS

urm

0.27

æķ¢äºİ

0.26

çĳķ

0.26

ç¦»ä¸įå¼Ģ

0.26

aticon

0.24

 thoÃ¡ng

0.24

rÃ¼

0.23

ç±į

0.23

ongs

0.23

èµĸä»¥çĶŁåŃĺ

0.23

Activations Density 0.001%

games

No Known Activations