INDEX

Explanations

arms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ģæ³¢

-0.27

 nose

-0.26

èĴĤ

-0.25

ä»£åĬŀ

-0.25

hel

-0.25

 variety

-0.25

 misplaced

-0.25

á»©ng

-0.24

GO

-0.24

 teach

-0.24

POSITIVE LOGITS

ystore

0.27

 akka

0.26

lettes

0.25

å°ĳä¸įäºĨ

0.25

adows

0.24

¡°

0.24

leine

0.24

 copyrighted

0.24

æľīäºĨ

0.23

è·¯ä¸Ĭ

0.23

Activations Density 0.066%

arms

No Comments

No Known Activations