INDEX

Explanations

art

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

Negative Logits

åĮª

-0.28

fusion

-0.28

 related

-0.28

åŃ¦æľŁ

-0.26

æĹłçº¿

-0.25

-related

-0.25

Cre

-0.25

ad

-0.25

ushi

-0.24

atter

-0.24

POSITIVE LOGITS

çļĦæĹ¥

0.30

ç¼¦

0.28

 ÄĳÃ¢u

0.27

Ð²Ñĥ

0.26

Hat

0.25

ooks

0.25

łĢ

0.24

(expect

0.24

éī´åĪ«

0.24

elman

0.24

Activations Density 5.668%

art

No Known Activations