INDEX

Explanations

purified

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

IsActive

-0.31

vature

-0.29

 isActive

-0.26

}//

-0.25

_TB

-0.25

Sus

-0.25

.INPUT

-0.24

sus

-0.24

oled

-0.24

 suspicions

-0.24

POSITIVE LOGITS

å¢ŀéĩı

0.29

 burn

0.28

å£ĳ

0.27

enschaft

0.26

ufen

0.26

åĴ½

0.26

ufe

0.25

 burns

0.25

 burner

0.24

ä¸ĩæĪ·

0.24

Activations Density 0.020%

purified

No Comments

No Known Activations