INDEX

Explanations

created by

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

otal

-0.30

uly

-0.28

æłĩ

-0.27

abox

-0.26

 cáº£nh

-0.25

å¥ĺ

-0.25

alar

-0.24

 investigating

-0.23

 Scha

-0.23

 lining

-0.23

POSITIVE LOGITS

åķ¬

0.31

nds

0.28

æĶ¹

0.28

æĸ¼æĺ¯

0.28

.payload

0.28

 Turning

0.26

(turn

0.25

mpr

0.25

 Greatest

0.24

 HEIGHT

0.24

Activations Density 0.003%

created by

No Comments

No Known Activations