INDEX

Explanations

computer code/documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isz

-0.27

åıĳå±ķä¸Ń

-0.27

å¼ķçĶ¨æĹ¥æľŁ

-0.27

aye

-0.26

PIC

-0.26

thr

-0.26

æİĴéĻ¤

-0.25

çĶŁæ´»åľ¨

-0.25

åįģäºĮæĿ¡

-0.25

isa

-0.24

POSITIVE LOGITS

éķ¿è¾Ī

0.28

çŁŃ

0.28

 shorter

0.28

çĥ¹

0.27

á»Ŀi

0.26

ynos

0.26

hort

0.26

áº£o

0.25

opr

0.25

BA

0.25

Activations Density 0.001%

computer code/documentation

No Comments

No Known Activations