INDEX

Explanations

the

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RAT

-0.30

éĴ®

-0.27

columnName

-0.26

åĵģ

-0.26

ADE

-0.26

çłĤ

-0.25

GroupName

-0.25

Ø§Ø¯

-0.24

èĥŃ

-0.24

 Goodman

-0.24

POSITIVE LOGITS

ursive

0.28

 hÃ´n

0.28

viders

0.27

orns

0.25

æ³ļ

0.25

å¯ºéĻ¢

0.25

æ¢¦è§ģ

0.25

 yourselves

0.24

ancellor

0.24

 HAND

0.24

Activations Density 0.047%

the

No Comments

No Known Activations