INDEX

Explanations

wealth

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

å£¬

-0.30

ax

-0.27

unt

-0.26

ä¸Ńéĥ¨

-0.25

ceed

-0.25

 Ø§ÙĦÙħÙĪØ³Ùħ

-0.25

>Title

-0.24

 Cara

-0.24

 outnumber

-0.24

alk

-0.24

POSITIVE LOGITS

éļ¾çĤ¹

0.30

ç®ĢåįķçļĦ

0.27

))-

0.26

Ã©ta

0.26

soup

0.26

lÃ©

0.26

 pools

0.25

ctrine

0.25

mans

0.25

çĶŁæ´»çļĦ

0.25

Activations Density 0.000%

wealth

No Comments

No Known Activations