INDEX

Explanations

renewal or repair

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

itter

-0.28

rar

-0.27

åĹĳ

-0.26

rene

-0.25

otyp

-0.25

åı¯èĥ½åŃĺåľ¨

-0.25

ä¼ģä¸ļæıĲä¾Ľ

-0.25

epy

-0.24

è§£éĶģ

-0.24

ç§ĺä¹¦

-0.24

POSITIVE LOGITS

distribution

0.29

æīĢæľīçļĦ

0.27

Rig

0.26

.desktop

0.26

rig

0.24

Appro

0.23

æīĢæľī

0.23

åįłæį®äºĨ

0.23

 GetAll

0.23

è¯´äºĨ

0.23

Activations Density 49.643%

renewal or repair

No Comments

No Known Activations