INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¾ÑĩÐµÐº

-0.28

ipt

-0.28

å®Ī

-0.28

Timing

-0.27

ä¸įåĲĮçļĦ

-0.27

æīĢåľ¨

-0.27

 timing

-0.26

Ð¾ÑĩÐºÐ¸

-0.26

å¼ı

-0.26

POSITIVE LOGITS

 dissert

0.28

 Graduate

0.27

 miser

0.27

è¿Ľä¿®

0.26

rello

0.25

ä¸Ńçº§

0.24

 Regents

0.24

 Thurs

0.24

è¢«èªī

0.24

 anything

0.24

Activations Density 1.813%

No Known Activations

This feature has no known activations.