INDEX

Explanations

Code/mathematical expressions

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

Negative Logits

finity

-0.24

ç¶ľåĲĪ

-0.24

 patented

-0.23

 mens

-0.23

sem

-0.23

illard

-0.23

lood

-0.23

 apologized

-0.23

 Singer

-0.23

 arrive

-0.22

POSITIVE LOGITS

çķĮçļĦ

0.27

&p

0.27

.Compiler

0.27

grounds

0.27

æľ¬ä¹¦

0.26

á»Ľt

0.24

åį°è±¡

0.24

 ApplicationController

0.23

.hr

0.23

CallCheck

0.23

Activations Density 0.584%

Code/mathematical expressions

No Known Activations