INDEX

Explanations

Julius/Julian

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

ayah

-0.30

 errorThrown

-0.27

nze

-0.25

peon

-0.24

 MODIFY

-0.24

 Fang

-0.24

 Crazy

-0.23

Sle

-0.23

 Mango

-0.23

 Democr

-0.23

POSITIVE LOGITS

å¯¹ä»ĸ

0.29

è®©æ¶Īè´¹èĢħ

0.26

æĭĪ

0.25

å¯¹äººä½ĵ

0.25

 onView

0.24

itto

0.24

lete

0.23

âĬĩ

0.23

 Short

0.23

(dead

0.23

Activations Density 0.005%

Julius/Julian

No Comments

No Known Activations