INDEX

Explanations

of

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

åĬłæģ¯

-0.28

æĸ¹åľĨ

-0.27

ãģ¶ãĤĬ

-0.26

(logits

-0.26

åľĪåŃĲ

-0.26

 Ð»Ð¸ÑĨÐ°

-0.25

éļĶå£ģ

-0.25

æĮĳ

-0.24

ç¢İçīĩ

-0.24

åĨħãģ®

-0.24

POSITIVE LOGITS

ihar

0.27

arin

0.27

 Injection

0.26

çº«

0.26

¹Ħ

0.25

è¶±

0.25

gps

0.25

tec

0.24

ataka

0.24

pea

0.24

Activations Density 0.003%

of

No Comments

No Known Activations