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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áĥ®

-0.24

æĳĩå¤´

-0.24

CAC

-0.23

ä»İä¸¥æ²»

-0.23

 emphas

-0.23

çĲħ

-0.23

æ²¹çĥŁ

-0.23

resents

-0.23

 Ð´Ð¾ÑħÐ¾Ð´

-0.23

 irradi

-0.23

POSITIVE LOGITS

 Joined

0.30

 specifier

0.28

elle

0.25

unos

0.25

 Conspiracy

0.25

Joined

0.24

atti

0.24

INI

0.24

ython

0.24

å¥½äºĭ

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.