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

ometer

-0.29

 brought

-0.27

è¸¬

-0.26

/Index

-0.26

 Tuesday

-0.25

æľīä¸¤ä¸ª

-0.25

unication

-0.24

 raised

-0.24

 development

-0.24

/index

-0.24

POSITIVE LOGITS

èģĶç½ĳ

0.28

å¤ªå¤ª

0.27

Reset

0.26

Ð¿Ð¾Ð´

0.26

çĦī

0.26

éĴİ

0.26

errer

0.25

æĲŃ

0.25

_reset

0.24

wich

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.