INDEX

Explanations

savings, reduction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/AFP

-0.28

Recursive

-0.26

ivant

-0.26

 Recursive

-0.25

/&

-0.24

åĺŀ

-0.24

æĥħåĨµè¿Ľè¡Į

-0.24

 Junk

-0.24

 Lucia

-0.24

oling

-0.24

POSITIVE LOGITS

 uninsured

0.24

htar

0.24

.PNG

0.24

åĿĬ

0.24

ippy

0.24

æĿ²

0.24

ç©°

0.24

æ³ķ

0.23

åı¸

0.23

mdat

0.23

Activations Density 11.460%

savings, reduction

No Comments

No Known Activations