INDEX

Explanations

contains the letter y

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 again

-0.28

æł·çļĦ

-0.28

 Again

-0.28

åºĲ

-0.28

Again

-0.27

æ¨£

-0.27

æł·

-0.26

Ð°Ð½Ñģ

-0.25

again

-0.25

ifik

-0.24

POSITIVE LOGITS

etsy

0.28

/terms

0.28

ç«ł

0.27

esti

0.26

 Roose

0.26

åŁİå¢Ļ

0.26

modx

0.25

sut

0.25

 facult

0.25

gue

0.24

Activations Density 0.004%

contains the letter y

No Comments

No Known Activations