INDEX

Explanations

government/business communications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è´¢æĶ¿éĥ¨

-0.29

å®ļäºĨ

-0.28

Jud

-0.28

è®©å®ĥ

-0.27

jud

-0.27

ÐµÑģÑĤÐ²

-0.27

åĽ½ä¼ļ

-0.26

 Agency

-0.26

itz

-0.25

.gov

-0.25

POSITIVE LOGITS

 Ã©c

0.27

ç¾ģ

0.25

BarItem

0.25

å¼ĢéĢļ

0.24

åĬ£

0.24

éŁ³

0.24

åŃĽ

0.24

äººäºº

0.24

pay

0.23

 resil

0.23

Activations Density 0.004%

government/business communications

No Comments

No Known Activations