INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igation

-0.27

ora

-0.26

zeit

-0.25

éĸĭæĶ¾

-0.24

omba

-0.24

 ullam

-0.24

uffs

-0.24

rique

-0.24

 fora

-0.24

harma

-0.23

POSITIVE LOGITS

æ¯į

0.31

ä¸įä¸ĭ

0.29

 family

0.27

æµĭ

0.27

ä»ħä»ħæĺ¯

0.27

ç¿ĺ

0.25

 Family

0.25

çļĦè®¤çŁ¥

0.25

%#

0.25

#"

0.24

Activations Density 3.151%

Code

No Comments

No Known Activations