INDEX

Explanations

contact information/organization

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

Ã´me

-0.29

è°®

-0.26

 phased

-0.26

æ¬¡

-0.25

straints

-0.25

occasion

-0.25

adar

-0.24

èĢĥèĻĳ

-0.24

orts

-0.24

íİľ

-0.24

POSITIVE LOGITS

 emailing

0.30

å¥½ä¸įå¥½

0.29

 email

0.29

éĤ®

0.28

or

0.28

email

0.27

 Email

0.26

Email

0.26

 asking

0.26

 whenever

0.26

Activations Density 0.003%

contact information/organization

No Comments

No Known Activations