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

lope

-0.24

ivable

-0.24

ichen

-0.24

 Moderate

-0.23

apsed

-0.23

.parseFloat

-0.23

 Dram

-0.23

ä»ħä¾Ľ

-0.23

åĲĮè¡Į

-0.22

ewidth

-0.22

POSITIVE LOGITS

etting

0.30

oning

0.27

æŀĦ

0.26

tat

0.26

itat

0.26

 ()↵↵

0.25

–↵↵

0.25

åĽĽåŃ£

0.24

zure

0.23

unger

0.23

Activations Density 0.031%

No Known Activations

This feature has no known activations.