INDEX

Explanations

Broad internet content

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

eurs

-0.28

uario

-0.25

mgr

-0.24

">#

-0.24

æĭ¼

-0.24

grand

-0.24

PELL

-0.23

Rem

-0.23

usp

-0.23

acÄ±

-0.23

POSITIVE LOGITS

ç»´æĬ¤

0.29

çĮ®è¡Ģ

0.28

vidence

0.27

è¿Ļä¹Īè¯´

0.27

è®¤å®ļ

0.26

å®ŀåľ°

0.26

æ¶²åİĭ

0.26

ulis

0.25

 collect

0.25

æµģåĬ¨æĢ§

0.24

Activations Density 0.007%

Broad internet content

No Comments

No Known Activations