INDEX

Explanations

Donald

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

ql

-0.29

Dry

-0.28

Dry

-0.27

 Ness

-0.26

inja

-0.26

-account

-0.25

accounts

-0.25

 accounts

-0.25

ookies

-0.24

ä¸Ŀä¸Ŀ

-0.24

POSITIVE LOGITS

.asList

0.27

ahren

0.25

è¥¿çº¢

0.24

caÃ§Ã£o

0.24

Ð¸Ð½ÑĦ

0.24

cano

0.24

 ÐºÑĥÐ»ÑĮÑĤÑĥÑĢÑĭ

0.24

conte

0.23

theon

0.23

 Scanner

0.23

Activations Density 0.026%

Donald

No Comments

No Known Activations