INDEX

Explanations

also

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EI

-0.28

verse

-0.28

ãģıãĤĮ

-0.27

 vice

-0.27

CppType

-0.25

vice

-0.25

æµı

-0.24

che

-0.24

<![

-0.24

 inade

-0.24

POSITIVE LOGITS

ingles

0.29

cvs

0.26

cul

0.25

ç»ĵæĿŁäºĨ

0.25

iniz

0.25

çĩİ

0.24

æ£¹

0.24

iclass

0.23

 siÃªu

0.23

Bulk

0.23

Activations Density 0.003%

also

No Comments

No Known Activations