INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĭ¢

-0.31

auge

-0.26

èĢģå¸Īä»¬

-0.26

å¤§å®¶

-0.26

orton

-0.26

åĢĵ

-0.25

pole

-0.25

arcy

-0.25

éĢĥè·ĳ

-0.24

æķĽ

-0.23

POSITIVE LOGITS

Liv

0.30

Liv

0.30

 thou

0.29

ç¨¼

0.28

liv

0.28

burgh

0.27

á»©

0.27

 Fork

0.27

 Floor

0.25

.iv

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.