INDEX

Explanations

Law and geography

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

usher

-0.30

anela

-0.26

 honorable

-0.26

oli

-0.25

ego

-0.25

 stir

-0.24

å¤§åĶĲ

-0.24

lep

-0.23

BackPressed

-0.23

åĬŀåħ¬æ¥¼

-0.23

POSITIVE LOGITS

èīĩ

0.29

ç»º

0.26

-proof

0.26

 Clubs

0.26

 club

0.26

identity

0.26

ë¹ł

0.25

å«ī

0.25

Lod

0.25

',{

0.25

Activations Density 0.003%

Law and geography

No Comments

No Known Activations