INDEX

Explanations

database/code

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

 Koreans

-0.36

æĺ¯éŁ©åĽ½

-0.32

 Korean

-0.29

lid

-0.29

 Simply

-0.28

kim

-0.27

Kak

-0.27

 HÃłn

-0.26

éŁ©åĽ½

-0.26

NAS

-0.26

POSITIVE LOGITS

olley

0.28

latin

0.26

åĲĮåŁİ

0.25

ÐĶÐķ

0.24

 plunge

0.24

:@

0.24

çĽ®æłĩä»»åĬ¡

0.24

åħ¥å¢ĥ

0.23

ç±³ç²ī

0.23

 extrad

0.23

Activations Density 0.001%

database/code

No Comments

No Known Activations