INDEX

Explanations

Wolfe

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çļĦåĵģçīĮ

-0.29

æ³ķå®ļ

-0.27

archy

-0.27

å°ıèħ¿

-0.26

å®ŀä½ĵç»ıæµİ

-0.26

vier

-0.26

tit

-0.25

 Georgetown

-0.24

ItemList

-0.24

.contentMode

-0.24

POSITIVE LOGITS

aven

0.27

åŃº

0.26

å·´å£«

0.26

orting

0.25

 infr

0.24

ä¸ĩæĪ·

0.24

èĹ©

0.24

åĲł

0.24

Native

0.24

Ð·Ð²Ð°Ð½

0.23

Activations Density 24.807%

Wolfe

No Comments

No Known Activations