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

ect

-0.28

ward

-0.27

 cent

-0.27

 sense

-0.25

éĴ®

-0.25

ìļķ

-0.25

Luke

-0.25

cent

-0.24

à¸¥à¸ĩ

-0.24

ASON

-0.24

POSITIVE LOGITS

å¯®

0.30

.firebaseapp

0.28

èĪį

0.26

æĹħè¡Į

0.26

dac

0.26

odal

0.25

repid

0.25

ä¸įå¾Ĺä¸įè¯´

0.24

å½Ĵ

0.24

ADVERTISEMENT

0.23

Activations Density 0.982%

No Known Activations

This feature has no known activations.