INDEX

Explanations

comparisons and statistics

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

åĨ³ä¸į

-0.28

ÑĢÐ°Ð¹

-0.28

&M

-0.26

åĨľä¸ļç§ĳæĬĢ

-0.26

å¤ªå¿«

-0.26

è¶ħå¼º

-0.25

 Shake

-0.25

æĳ§

-0.25

å§ĭç»ĪåĿļæĮģ

-0.25

à¤ŀ

-0.23

POSITIVE LOGITS

 closed

0.29

zimmer

0.28

_closed

0.28

æĹ¥èµ·

0.26

Closed

0.26

ç¤¾

0.25

avia

0.24

 Closed

0.24

ities

0.24

ÙĥÙĬ

0.24

Activations Density 0.003%

comparisons and statistics

No Comments

No Known Activations