INDEX

Explanations

Describing changes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

vious

-0.27

åĬłå·¥åİĤ

-0.26

 ours

-0.24

ifold

-0.24

/doc

-0.24

åŃ¦çĶŁä»¬

-0.24

Tbl

-0.23

izo

-0.23

æĥ³è±¡

-0.23

åĵ²

-0.23

POSITIVE LOGITS

 Radical

0.30

cub

0.30

åĴ¸

0.28

wear

0.26

è¦ģç´§

0.26

thumbs

0.26

 Publishing

0.26

 contrib

0.25

gies

0.25

Cub

0.25

Activations Density 1.418%

Describing changes

No Known Activations