INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isz

-0.30

 exact

-0.26

 station

-0.26

 hoÃłng

-0.26

ä¸įåħĭ

-0.26

 each

-0.25

åı£å¾Ħ

-0.25

uran

-0.25

CDC

-0.25

Dec

-0.25

POSITIVE LOGITS

å¾®åŀĭ

0.28

ypi

0.27

è¹Ī

0.27

onso

0.26

ç³ķ

0.26

åľ³

0.26

æīĢæıĲä¾Ľä¹ĭ

0.26

mina

0.26

ä¸ĭéĿ¢æĺ¯å°ı

0.26

æµģåĩº

0.26

Activations Density 0.003%

code

No Comments

No Known Activations