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

Negative Logits

prs

-0.38

head

-0.27

 head

-0.26

lÃ¼

-0.25

å¯º

-0.24

trs

-0.24

.describe

-0.24

 Enlight

-0.23

éĨ¢

-0.23

 shower

-0.23

POSITIVE LOGITS

ĽĦ

0.28

è¶Ĭ

0.26

owned

0.24

estination

0.23

 Weiner

0.23

ä¸ļçķĮ

0.23

/weather

0.23

åķĨæĬ¥

0.23

ornment

0.23

Va

0.23

Activations Density 0.154%

No Known Activations

This feature has no known activations.