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

IPP

-0.30

umper

-0.29

ÅĤad

-0.29

 Humph

-0.27

inality

-0.27

[keys

-0.26

Dragging

-0.26

 hÃ´

-0.25

PIE

-0.25

 Rudd

-0.24

POSITIVE LOGITS

åĮ¹

0.27

 sheer

0.26

éģĹä¼ł

0.26

å³Ń

0.26

him

0.25

at

0.24

ä¸įå¹³è¡¡

0.23

 toute

0.23

 groom

0.23

enticate

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.