INDEX

Explanations

the

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

 Ð°Ð²Ð³ÑĥÑģÑĤÐ°

-0.27

æĶ¶æķĽ

-0.26

')</

-0.26

è½½

-0.25

æĺ¯åĽłä¸º

-0.25

lian

-0.25

ä»Ģä¹ĪåİŁåĽł

-0.25

çļĩåŃĲ

-0.24

 submitting

-0.24

ä¸įå¤±

-0.24

POSITIVE LOGITS

 locus

0.28

 region

0.28

 regional

0.27

åĮºåŁŁ

0.27

arently

0.26

å¸ĤåľºåĮĸ

0.26

 Regional

0.25

åĴĮåľ°åĮº

0.25

çĿĢçľ¼

0.25

region

0.25

Activations Density 0.027%

the

No Comments

No Known Activations