INDEX

Explanations

/

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

Ass

-0.27

 Over

-0.27

 Right

-0.25

rÃŃ

-0.25

ç®

-0.24

 eBay

-0.24

ìĦ¸ìļĶ

-0.24

ContextHolder

-0.24

åį³åı¯

-0.24

forge

-0.24

POSITIVE LOGITS

 lÆ°á»Ľi

0.30

çļĦå£°éŁ³

0.27

åĬŀåħ¬å®¤

0.27

vern

0.26

Ã©sz

0.25

entially

0.25

 genetically

0.25

isure

0.24

 arbitrarily

0.24

çļĦåħ³æ³¨

0.24

Activations Density 0.020%

/

No Comments

No Known Activations