INDEX

Explanations

_fac

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

 dÃ©t

-0.28

åĻ¤

-0.27

 PATCH

-0.27

ä¸ģ

-0.25

 interoper

-0.25

pres

-0.25

 intersection

-0.25

PATCH

-0.25

 HttpClientModule

-0.25

 concentrated

-0.24

POSITIVE LOGITS

ITO

0.29

apur

0.27

ifndef

0.27

åĨįçĶŁ

0.26

emas

0.26

apel

0.25

å»ĵ

0.25

åĽ¢åĳĺ

0.25

DER

0.25

 Lebens

0.24

Activations Density 0.003%

_fac

No Comments

No Known Activations