INDEX

Explanations

hair

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

ê´Ģ

-0.28

pos

-0.28

bag

-0.27

ä¸ĭæĿ¥

-0.26

bag

-0.26

zion

-0.26

ä¸ĭä¾Ĩ

-0.25

 today

-0.25

pos

-0.24

åĿļå®Ī

-0.24

POSITIVE LOGITS

-tm

0.30

 outdoor

0.28

TEX

0.27

ç¬¬äºĮç§į

0.26

è¿Ļä¸¤ç§į

0.26

 Outdoor

0.26

–and

0.25

Outdoor

0.25

éĽªå±±

0.25

æį»

0.24

Activations Density 0.007%

hair

No Comments

No Known Activations