INDEX

Explanations

math, programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pike

-0.30

aby

-0.27

UIP

-0.26

 vÃ¶

-0.26

entai

-0.25

olean

-0.25

å¤§çº¦

-0.25

 polic

-0.25

ragments

-0.24

pik

-0.24

POSITIVE LOGITS

ads

0.28

å±Ģ

0.26

 guts

0.26

AVE

0.25

irs

0.24

.SceneManagement

0.24

 Elev

0.23

 Ames

0.23

Media

0.23

ä¸»

0.23

Activations Density 0.004%

math, programming

No Comments

No Known Activations