INDEX

Explanations

exams

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 Glass

-0.25

cr

-0.25

é¡¿

-0.25

amic

-0.25

 maint

-0.24

etty

-0.24

æľ«

-0.24

åľ¨ç¾İåĽ½

-0.23

ç²Ĺ

-0.23

ombres

-0.23

POSITIVE LOGITS

acie

0.28

charge

0.27

bur

0.27

è¯ĦåĪ¤

0.27

æŀķå¤´

0.25

éĽ·éľĨ

0.25

 Ð¾Ð³ÑĢÐ°Ð½Ð¸ÑĩÐµÐ½

0.25

åĮħåĽ´

0.24

(--

0.24

OSC

0.24

Activations Density 0.002%

exams

No Comments

No Known Activations