INDEX

Explanations

email subscriptions

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

æĹ¶æĬ¥

-0.27

istani

-0.26

å¥½å¥½

-0.26

ankind

-0.25

ijing

-0.24

éªĭ

-0.24

 Ipsum

-0.24

-Russian

-0.24

anoi

-0.24

ç«ŀèµĽ

-0.24

POSITIVE LOGITS

ä¸ªäºº

0.32

 personal

0.32

personal

0.29

ButtonText

0.28

arium

0.28

 Personal

0.28

åĢĭäºº

0.28

 Clair

0.26

å¸®åĬ©

0.25

exp

0.25

Activations Density 0.003%

email subscriptions

No Comments

No Known Activations