INDEX

Explanations

Latin

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

pain

-0.29

rac

-0.28

 pain

-0.27

 ÑĢÐ°

-0.26

ä¸įå¹³è¡¡

-0.26

 Pain

-0.26

ç¿¦

-0.26

Ãºa

-0.25

ç«ŀ

-0.25

rÃ©

-0.25

POSITIVE LOGITS

åı¤ä»£

0.26

éģ¥è¿ľ

0.25

noÅĽÄĩ

0.25

 toItem

0.25

é¡ºåºı

0.24

å¡

0.24

ToFront

0.24

osaic

0.24

igkeit

0.24

æĻ®åıĬ

0.23

Activations Density 5.308%

Latin

No Comments

No Known Activations