INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

.googleapis

-0.28

 Strategy

-0.26

antom

-0.26

ruk

-0.25

mainwindow

-0.25

luent

-0.24

iquement

-0.24

å½ĵä»£

-0.24

Strategy

-0.24

taken

-0.24

POSITIVE LOGITS

éĺ²æĻĴ

0.27

 Hayward

0.25

ä¸ŃéĢĶ

0.25

 comps

0.25

usive

0.23

petition

0.23

Am

0.23

lÃ¤ss

0.23

.nodeType

0.22

çīĪæĿĥæīĢæľī

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.