INDEX

Explanations

mes

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

å¼¹

-0.31

rend

-0.27

efore

-0.27

çº¿ç´¢

-0.27

itter

-0.25

å½Ī

-0.25

me

-0.24

ame

-0.24

Cue

-0.24

ome

-0.24

POSITIVE LOGITS

·æĸ°

0.29

icap

0.28

ä¸įæĸŃçļĦ

0.27

åĿĹ

0.26

.assets

0.25

INO

0.25

Ä±klÄ±

0.25

åħ¨èµĦåŃĲ

0.24

bara

0.24

ino

0.24

Activations Density 1.288%

mes

No Comments

No Known Activations