INDEX

Explanations

ashi

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

è§¸

-0.29

çĳ¶

-0.29

è§¦

-0.28

ðŁĴ¡

-0.27

è§ģéĿ¢

-0.27

ãģĻãĤĭãģ¨

-0.27

æ¸¸æĪıæĬĢå·§

-0.26

fac

-0.25

å¤§å¥ĸ

-0.25

iones

-0.24

POSITIVE LOGITS

otas

0.28

ä¿®

0.27

 swear

0.27

 Jerusalem

0.25

é¡¾

0.25

ä¹ĺ

0.24

 Decor

0.24

åĨ¤

0.24

ä¹ī

0.24

.UnitTesting

0.24

Activations Density 0.003%

ashi

No Comments

No Known Activations