INDEX

Explanations

math equations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

initely

-0.27

éĽ¹

-0.26

 simply

-0.25

é¦Ĵ

-0.25

(Unit

-0.25

kÃ¶p

-0.25

odos

-0.24

ayscale

-0.24

èķŀ

-0.23

wap

-0.23

POSITIVE LOGITS

èĬĤ

0.30

these

0.28

 alternative

0.25

ÑĢÐ¾Ð²ÐµÑĢ

0.24

è¿Ļåĩłä¸ª

0.24

lst

0.24

åı¦

0.24

 convolution

0.24

 conv

0.23

ystal

0.23

Activations Density 0.001%

math equations

No Known Activations