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

ç±»ä¼¼çļĦ

-0.30

åģļåĪ°

-0.26

ç´į

-0.24

æĥ³è¿ĩ

-0.24

å¯¹åºĶçļĦ

-0.24

\$

-0.23

çī¹æ®ĬçļĦ

-0.23

å¢ĥçķĮ

-0.23

 warfare

-0.23

pector

-0.23

POSITIVE LOGITS

-Cs

0.29

æŁŀ

0.29

-round

0.28

æĹħ

0.27

 gent

0.25

InstanceState

0.25

 ROUND

0.25

.cloudflare

0.25

æķŀ

0.25

mtx

0.25

Activations Density 3.825%

No Known Activations

This feature has no known activations.