INDEX

Explanations

code and technical content

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

 craft

-0.28

Ø«Ø§Ø±

-0.27

åĨ²

-0.27

èĮ¨

-0.27

setContent

-0.26

å¿Ĺ

-0.26

icina

-0.26

ç»İ

-0.25

ç»¸

-0.25

é½¿

-0.25

POSITIVE LOGITS

æĽ´å¥½çļĦ

0.28

åıĸåĨ³

0.28

æĽ´å¥½

0.25

 csvfile

0.25

eler

0.24

æĽ´ä½İ

0.24

 Better

0.24

OrDefault

0.24

äºĭçī©

0.24

etype

0.24

Activations Density 0.010%

code and technical content

No Comments

No Known Activations