INDEX

Explanations

printed

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

èĩ

-0.29

lops

-0.28

 leveled

-0.27

ystack

-0.25

leys

-0.25

 CoreData

-0.25

 Meet

-0.25

busters

-0.24

ensored

-0.24

 Prison

-0.24

POSITIVE LOGITS

ç¥¨æį®

0.33

è¿Ļå¼ł

0.32

-pattern

0.28

 patterns

0.28

åį°èĬ±

0.27

çĶŁæķĪ

0.27

èĬ±çº¹

0.26

æĦĪ

0.26

åķĨæłĩ

0.26

åĵģ

0.25

Activations Density 0.203%

printed

No Comments

No Known Activations