INDEX

Explanations

quotation marks

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

igin

-0.28

mans

-0.26

uest

-0.26

åĭķ

-0.25

ill

-0.25

ukt

-0.25

ivent

-0.25

åĬ¨

-0.25

fullscreen

-0.25

 advent

-0.25

POSITIVE LOGITS

sembly

0.28

 dong

0.26

conomy

0.25

åķĨä¼ļ

0.25

getReference

0.25

ç½ĳåĿĢ

0.24

IllegalAccessException

0.24

coder

0.23

 ÑģÑģÑĭÐ»

0.23

caÃ§Ã£o

0.23

Activations Density 0.003%

quotation marks

No Comments

No Known Activations