INDEX

Explanations

plastic

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

åĨħå®¹

-0.30

name

-0.27

é«ĵ

-0.26

åħ§å®¹

-0.25

dress

-0.25

æŃ¦

-0.25

ä½Ļé¢Ŀ

-0.25

 within

-0.25

äºİ

-0.24

inal

-0.24

POSITIVE LOGITS

è¿ĽåŁİ

0.27

æĹ¶ä»£

0.27

onest

0.26

Ã©tude

0.25

åħ¬ç¤¾

0.25

 tÃ´

0.25

 SchÃ¶n

0.24

lassian

0.24

GetInstance

0.24

oon

0.24

Activations Density 0.003%

plastic

No Comments

No Known Activations