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

_REGS

-0.29

ÅĦ

-0.28

åĪ®

-0.27

brero

-0.26

ancial

-0.26

imo

-0.25

ician

-0.25

ylinder

-0.25

Õ®

-0.25

(($

-0.25

POSITIVE LOGITS

 getUrl

0.25

oad

0.25

è¤¡

0.25

mi

0.25

 getClass

0.24

ä¼ļè®©ä½ł

0.24

eti

0.24

çĲ¢ç£¨

0.24

å¸®æĪĳ

0.24

å¯¹æĪĳ

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.