INDEX

Explanations

the

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

-dismissible

-0.27

 Procedure

-0.26

akra

-0.25

ä½łèĩªå·±

-0.25

 hints

-0.25

æ¶Īè´¹èĢħçļĦ

-0.25

åİŁåĪĻ

-0.24

.Bunifu

-0.24

æĪĳèĩªå·±

-0.24

äºĴ

-0.24

POSITIVE LOGITS

aux

0.38

rm

0.26

PO

0.26

æĿ³

0.25

 âĪĪ

0.25

è®¨

0.24

aux

0.24

ROM

0.23

æĺ¯åĽ½åĨħ

0.23

IM

0.23

Activations Density 0.131%

the

No Comments

No Known Activations