INDEX

Explanations

agon

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

 black

-0.27

Black

-0.25

 Black

-0.25

åĩĿèģļ

-0.25

éĢĢ

-0.25

éĿŀæ´²

-0.25

é»ĳ

-0.24

idis

-0.24

æľĢåĪĿ

-0.24

BuilderInterface

-0.24

POSITIVE LOGITS

 Rockefeller

0.28

åł°

0.26

emony

0.25

éŁ³

0.24

 relev

0.24

ycin

0.24

ÐµÐ¼ÑĭÐµ

0.24

SAME

0.24

Hit

0.24

enes

0.24

Activations Density 0.035%

agon

No Comments

No Known Activations