INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĺ¯ä¸įæĺ¯

-0.30

{}]

-0.29

zel

-0.26

ä¹ĭç¾İ

-0.26

zion

-0.25

iten

-0.24

odian

-0.24

icipation

-0.23

 Covent

-0.23

äºĨä¸Ģåı¥

-0.23

POSITIVE LOGITS

ç¼©

0.30

å²ģæľĪ

0.27

æ¢Ń

0.27

Ð¾ÑĢÑĤ

0.27

emplo

0.27

ighted

0.27

encil

0.26

ekte

0.26

å¬°

0.26

.CreateInstance

0.25

Activations Density 0.002%

No Known Activations

This feature has no known activations.