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

å¥

-0.30

 Disqus

-0.29

ple

-0.28

ä¹į

-0.28

+[

-0.27

å¤©åľ°

-0.27

Vert

-0.26

ä¸İåħ¶ä»ĸ

-0.25

åĴĽ

-0.25

 Vert

-0.25

POSITIVE LOGITS

æĭĽèĤ¡

0.29

 meanwhile

0.28

 harvest

0.26

semblies

0.26

UNU

0.24

å¼Ľ

0.24

åħ¬å¼Ģåıĳè¡Į

0.24

 CONVERT

0.24

cased

0.23

ÑĦÐ¾ÑĢ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.