INDEX

Explanations

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-bin

-0.24

 QGraphics

-0.24

Ä±z

-0.23

ðĿľĥ

-0.23

-spin

-0.23

cons

-0.23

 comment

-0.22

edo

-0.22

æķĻåŃ¸

-0.22

]=-

-0.22

POSITIVE LOGITS

osto

0.27

 somehow

0.26

 Punch

0.25

Chr

0.25

DataFrame

0.24

å®ļåĲĳ

0.24

cline

0.24

PathComponent

0.24

kinson

0.24

iteDatabase

0.23

Activations Density 0.037%

the

No Known Activations