INDEX

Explanations

JavaScript code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eson

-0.28

çĲĨ

-0.28

unge

-0.25

ransition

-0.25

 Hera

-0.25

é»ĳé¾Ļ

-0.24

åĮ¿åĲį

-0.24

åħ³çĪ±

-0.24

æ¶īåıĬåĪ°

-0.23

anker

-0.23

POSITIVE LOGITS

.setWindowTitle

0.26

limits

0.26

ddy

0.25

MOVE

0.25

 xtype

0.25

KW

0.24

ÑĻ

0.24

eware

0.24

èĢ¸

0.24

çĸ²

0.24

Activations Density 0.013%

JavaScript code

No Comments

No Known Activations