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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gone

-0.27

æĪĽ

-0.25

cop

-0.24

çī¹æķĪ

-0.24

argc

-0.24

 diesel

-0.24

æ²ī

-0.24

Gut

-0.23

Nr

-0.23

vvm

-0.23

POSITIVE LOGITS

ä½ľèĢħæľ¬äºº

0.29

ä¼ģä¸ļæıĲä¾Ľ

0.27

åĳ¨æľŁ

0.27

çİĩè¾¾åĪ°

0.26

ellar

0.26

çĶ¨èĩªå·±çļĦ

0.25

 expense

0.25

å½¹

0.25

åı¯èĥ½å¯¼èĩ´

0.25

 Period

0.25

Activations Density 0.233%

No Known Activations

This feature has no known activations.