INDEX

Explanations

concerned

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

éĿ¢

-0.32

esModule

-0.28

bol

-0.26

izu

-0.26

éĩĮéĿ¢æľī

-0.25

è¦ģå®³

-0.25

éĢļçŁ¥

-0.25

 notify

-0.24

ä¹¦éĿ¢

-0.24

ubi

-0.24

POSITIVE LOGITS

rays

0.29

å¾¹

0.25

 Binder

0.25

ordes

0.25

ä¸Ŀä¸Ŀ

0.24

á»ĵng

0.24

åĶ

0.24

 crunchy

0.23

æİĽãģĳ

0.23

 Scandinavian

0.23

Activations Density 2.014%

concerned

No Comments

No Known Activations