INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¹Łæ²¡ä»Ģä¹Ī

-0.29

ools

-0.27

cnt

-0.25

riba

-0.25

|i

-0.25

æ²¡ä»Ģä¹Ī

-0.24

opa

-0.24

ala

-0.24

ris

-0.24

ulo

-0.24

POSITIVE LOGITS

lement

0.26

elu

0.25

typeparam

0.25

rypto

0.25

lycer

0.25

è²ī

0.24

olon

0.24

-collapse

0.24

åľĺ

0.24

oldt

0.24

Activations Density 33.655%

No Known Activations

This feature has no known activations.