INDEX

Explanations

medicine

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ´²

-0.28

xFB

-0.25

Bol

-0.25

è°®

-0.24

ypy

-0.24

ipy

-0.24

DetailView

-0.23

å½ĵåīįä½įç½®

-0.23

oload

-0.23

Ã©rique

-0.23

POSITIVE LOGITS

łģ

0.28

æĶ¹åĪ¶

0.27

 hectares

0.26

ZH

0.26

ä¼łåĬ¨

0.25

KH

0.25

çĥŃæĥħ

0.25

ventions

0.24

Ãºb

0.24

 Legends

0.24

Activations Density 0.001%

medicine

No Comments

No Known Activations