INDEX

Explanations

protection

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

çĹķ

-0.33

Short

-0.28

 Mack

-0.26

.Formatter

-0.25

æķ£åıĳ

-0.24

 Short

-0.24

 flush

-0.24

imated

-0.24

Smith

-0.24

æįŀ

-0.24

POSITIVE LOGITS

éĺ²æŃ¢

0.37

ä¿ĿèŃ·

0.32

èŃ¦æĥķ

0.31

èŃ·

0.30

ä¿ĿæĬ¤

0.30

 prevent

0.30

é¢Ħéĺ²

0.29

ä»¥éĺ²

0.29

rote

0.29

 protect

0.29

Activations Density 0.004%

protection

No Comments

No Known Activations