INDEX

Explanations

components/parts

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

 witnessed

-0.27

äºĭæķħåıĳçĶŁ

-0.27

 atomic

-0.26

 fair

-0.26

atomic

-0.25

åħ¬å¹³

-0.25

éĴ±

-0.25

ient

-0.24

å¸ĺ

-0.24

èªĵ

-0.24

POSITIVE LOGITS

 HOME

0.28

ä¸Ģå®¶

0.27

 Â«

0.27

Â«

0.27

stalk

0.27

æ±©

0.25

 Descriptor

0.24

refs

0.24

Mer

0.24

 RETURN

0.23

Activations Density 0.810%

components/parts

No Comments

No Known Activations