INDEX

Explanations

patents

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

 Mull

-0.27

ieÅ¼

-0.27

operate

-0.26

ozo

-0.26

 cref

-0.26

ackle

-0.25

ç³ģ

-0.25

æĬ¢æķĳ

-0.25

MW

-0.25

coe

-0.24

POSITIVE LOGITS

 hall

0.29

åİħ

0.29

 Placement

0.28

å»³

0.27

 hood

0.27

sten

0.26

anky

0.26

 Ð¾Ð±Ð»Ð°

0.25

ipt

0.25

hall

0.24

Activations Density 0.061%

patents

No Comments

No Known Activations