INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IMS

-0.27

ä¸ĢèĦļ

-0.27

èµ·

-0.27

æľīä»»ä½ķ

-0.26

èĻŀ

-0.26

patches

-0.25

æĶĺ

-0.24

Ð»Ð¾Ð³

-0.24

 analysed

-0.24

acious

-0.24

POSITIVE LOGITS

-than

0.28

 Morse

0.26

 setObject

0.26

 Torres

0.24

ese

0.24

ä¼łåĩº

0.24

 priorities

0.24

·æĸ°

0.24

essen

0.24

 Alien

0.24

Activations Density 1.525%

No Known Activations

This feature has no known activations.