INDEX

Explanations

Places and Alphabet letters

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

quent

-0.31

ä¸įèĩ³äºİ

-0.28

 Yours

-0.28

 Family

-0.27

å°¤ä¸ºéĩįè¦ģ

-0.26

asty

-0.26

 Computing

-0.26

 Fired

-0.26

ewan

-0.26

fam

-0.26

POSITIVE LOGITS

èµ·

0.29

å¼Ĥ

0.29

ger

0.29

rella

0.27

ger

0.27

pin

0.27

æĶ

0.27

 Lords

0.27

ç¥Ń

0.27

ium

0.26

Activations Density 0.002%

Places and Alphabet letters

No Comments

No Known Activations