INDEX

Explanations

medical research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¿¡æģ¯åıĳå¸ĥ

-0.26

Broken

-0.25

.UnitTesting

-0.25

-ending

-0.25

yt

-0.25

orget

-0.24

DateFormat

-0.24

 pause

-0.24

chedules

-0.24

ãģ¨ãģ¯

-0.24

POSITIVE LOGITS

åĪ°å¤Ħ

0.28

ç»Ŀå¤§éĥ¨åĪĨ

0.28

 every

0.28

.every

0.27

å¤Ħå¤Ħ

0.26

 mostly

0.26

æ¡£

0.25

è¦ģä¹Ī

0.25

 issues

0.25

 wherever

0.25

Activations Density 0.007%

medical research

No Comments

No Known Activations