INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

åħļç»Ħ

-0.29

LEY

-0.27

å®Łãģ¯

-0.26

åĬ«

-0.25

@protocol

-0.24

éľģ

-0.24

 kostenlos

-0.24

-Re

-0.24

åħļç»ĦæĪĲåĳĺ

-0.24

pta

-0.23

POSITIVE LOGITS

çıī

0.27

lood

0.25

 invaders

0.24

 holes

0.24

ç²īæľ«

0.24

ë¹Ļ

0.24

oke

0.24

åŃ¦çĶŁçļĦ

0.23

 Ð¾ÑĢÐ³

0.23

 ------------------------------------------------

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.