INDEX

Explanations

ray/electron

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç§ĳåĪĽ

-0.26

æĲŃå»º

-0.24

à¹Ĥ

-0.24

ç¿³

-0.24

ÑĽ

-0.24

 keypoints

-0.24

æł¸éħ¸æ£Ģæµĭ

-0.24

ç¼©

-0.24

aca

-0.23

cic

-0.23

POSITIVE LOGITS

-src

0.28

Ð¸ÑĩÐµÑģÐºÐ¸Ð¼

0.25

 Euro

0.24

Euro

0.24

 MILL

0.24

Ã¶z

0.24

ienne

0.23

 separately

0.23

pies

0.23

maal

0.23

Activations Density 0.001%

ray/electron

No Comments

No Known Activations