INDEX

Explanations

Code/technical documentation

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

çļĦå½¢è±¡

-0.29

 shape

-0.26

Unnamed

-0.26

åĲ¯åıĳ

-0.26

Executable

-0.25

indh

-0.24

.future

-0.24

 hÃ¬nh

-0.24

å½¢

-0.23

çĻŀ

-0.23

POSITIVE LOGITS

ises

0.30

ussian

0.27

lit

0.26

elas

0.24

fan

0.24

 gaussian

0.23

PickerController

0.23

ä¸įè¶³ä»¥

0.23

peon

0.23

lob

0.23

Activations Density 0.001%

Code/technical documentation

No Comments

No Known Activations