INDEX

Explanations

code snippets

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

 borderBottom

-0.29

rost

-0.28

Ð±Ð¸

-0.27

otr

-0.25

Bu

-0.25

 Bark

-0.24

åį¢

-0.24

Top

-0.24

 Head

-0.23

Any

-0.23

POSITIVE LOGITS

 WindowManager

0.27

addWidget

0.27

Ð´Ð°Ð²

0.25

Ļ¶

0.24

 provision

0.24

 conv

0.24

deen

0.23

 Placement

0.23

 sacr

0.23

ucceed

0.23

Activations Density 0.011%

code snippets

No Comments

No Known Activations