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

ocache

-0.31

,row

-0.25

 Decomp

-0.24

-ons

-0.24

Particles

-0.24

ä»¥å¾Į

-0.23

planation

-0.23

äºĨä¸Ģä»½

-0.23

 wspÃ³ÅĤ

-0.23

umo

-0.23

POSITIVE LOGITS

 twink

0.29

startIndex

0.26

ä¸ªå¤ļ

0.26

æ¶Īè´¹èĢħçļĦ

0.26

ç¥¥

0.25

çļĦæĶ¯æĮģ

0.25

 resil

0.25

va

0.25

å®īç½®

0.25

ä¸°å¯Į

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.