INDEX

Explanations

:'

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

zen

-0.29

 degraded

-0.28

dater

-0.28

peat

-0.28

 planning

-0.27

æĳ¸

-0.26

egis

-0.26

 Ã¥

-0.26

ensch

-0.25

ÐµÑģÑĤ

-0.25

POSITIVE LOGITS

åľĦ

0.26

 Swords

0.26

éĥ½ä¸į

0.25

çķ¥

0.25

kehr

0.25

åºŁ

0.25

 IonicPage

0.24

 endings

0.24

åĲģ

0.24

iaux

0.24

Activations Density 0.010%

:'

No Comments

No Known Activations