INDEX

Explanations

ese

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ÑĥÑģÑĤ

-0.28

este

-0.26

 claimed

-0.25

PS

-0.25

ĥĿ

-0.25

åĲ¹

-0.24

abh

-0.24

ara

-0.24

å¤§å®¶

-0.24

åŁºæķ°

-0.23

POSITIVE LOGITS

é¢ĳé¢ĳ

0.26

 Serving

0.25

 towers

0.25

 Yourself

0.25

èĽ²

0.24

ENCED

0.24

 yourselves

0.24

 ourselves

0.24

 Gameplay

0.23

 illusions

0.23

Activations Density 0.250%

ese

No Known Activations