INDEX

Explanations

HTML code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ij

-0.33

æ¥ļ

-0.28

-0.27

Patch

-0.27

Pet

-0.26

SI

-0.26

CS

-0.26

ola

-0.26

est

-0.25

LT

-0.25

POSITIVE LOGITS

Hed

0.29

çĮĿ

0.28

ä¸įè¦ģ

0.27

ç¼©æ°´

0.27

Ð´Ð¾Ð½

0.26

hed

0.25

 Dealers

0.25

 CreateMap

0.24

 wearer

0.24

 dressing

0.24

Activations Density 0.013%

HTML code

No Comments

No Known Activations