INDEX

Explanations

changes

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

é¡¿

-0.29

ç§«

-0.27

æĹ©

-0.26

.findBy

-0.25

æľįåĬ¡ä¸ļ

-0.25

 behaviours

-0.25

inesis

-0.25

åıįè½¬

-0.25

 behaviour

-0.24

è¿Ļä¸ªæ¸¸æĪı

-0.24

POSITIVE LOGITS

insky

0.28

arp

0.27

Obs

0.27

__))

0.26

Ð·Ð½Ð°

0.26

è¯Ĩ

0.25

tml

0.25

 Heavenly

0.24

olars

0.24

 critically

0.24

Activations Density 0.013%

changes

No Comments

No Known Activations