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

esta

-0.31

opsis

-0.26

 intermediary

-0.24

.setViewportView

-0.24

 newcomers

-0.24

 newcomer

-0.23

 investing

-0.23

_MEDIUM

-0.23

adin

-0.23

,,,,

-0.23

POSITIVE LOGITS

æł½

0.28

ç»ĦåĽ¢

0.28

ä»ĸå¯¹

0.26

å¯¹ä¸ŃåĽ½

0.25

airo

0.25

äººä»¬å¯¹

0.24

Ã³rio

0.24

å°±å¥½äºĨ

0.24

 windshield

0.24

oriously

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.