INDEX

Explanations

Code/text with special characters

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 verd

-0.28

lux

-0.27

ewise

-0.25

æĹģè¾¹çļĦ

-0.24

—that

-0.24

Tam

-0.24

æĳĦ

-0.24

UV

-0.23

æį¶

-0.23

ething

-0.23

POSITIVE LOGITS

Ð´ÑĢ

0.30

azo

0.27

åŀ¸

0.27

icles

0.26

reduce

0.24

hra

0.24

 reduced

0.24

åĩı

0.24

.Constraint

0.24

obble

0.24

Activations Density 0.004%

Code/text with special characters

No Comments

No Known Activations