INDEX

Explanations

’

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

enario

-0.28

æĮĩå°ĸ

-0.26

cling

-0.26

ships

-0.25

å»ºçŃĳæĿĲæĸĻ

-0.25

eras

-0.25

 discovered

-0.24

æ°ĳæĹıæĸĩåĮĸ

-0.24

æľīä»·åĢ¼çļĦ

-0.24

!</

-0.23

POSITIVE LOGITS

æ²ģ

0.28

ineTransform

0.26

[in

0.25

 há»£p

0.25

 Citation

0.25

 unge

0.24

inen

0.24

ä¸Ģå¯¹

0.24

æŃĩ

0.24

æĮī

0.24

Activations Density 7.962%

’

No Comments

No Known Activations