INDEX

Explanations

set

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

å±ķå¼Ģ

-0.29

éĩĮçļĦ

-0.27

PMENT

-0.26

iting

-0.26

cion

-0.25

éĶ¹

-0.25

|-

-0.25

ãĤ¹ãĥĶ

-0.24

åĩĨ

-0.24

 vista

-0.24

POSITIVE LOGITS

æ²±

0.25

å¼¢

0.24

 trackers

0.24

Ð½Ð¾ÑģÑĤ

0.24

 Äĳá»Ŀi

0.24

 imports

0.24

 interactions

0.23

æ¹«

0.23

 posts

0.23

 reports

0.23

Activations Density 0.238%

set

No Comments

No Known Activations