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

arl

-0.27

GMC

-0.26

rench

-0.26

AMA

-0.24

 pots

-0.24

orate

-0.24

æĥ¯ä¾ĭ

-0.23

ellan

-0.23

resher

-0.23

 Persian

-0.23

POSITIVE LOGITS

ClassLoader

0.28

æľīäºº

0.26

ucht

0.25

inoa

0.25

eping

0.24

ç¼ħ

0.23

 impunity

0.23

å¹³éĿĻ

0.23

Download

0.23

fold

0.23

Activations Density 0.442%

No Known Activations

This feature has no known activations.