INDEX

Explanations

code

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

bian

-0.34

çģı

-0.28

agic

-0.28

iel

-0.28

alcon

-0.28

 quis

-0.27

EGIN

-0.26

'||

-0.26

 cord

-0.25

ç»¦

-0.25

POSITIVE LOGITS

èµ·ä¼ı

0.31

fall

0.26

odb

0.26

å¼ķè¿Ľ

0.26

AttributeValue

0.26

åĤ¾

0.25

-pressure

0.25

dew

0.25

.FIELD

0.25

çĥ¤

0.24

Activations Density 2.562%

code

No Comments

No Known Activations