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

vice

-0.28

quo

-0.28

çĿĽ

-0.27

ExecutionContext

-0.26

 *,↵

-0.25

NetMessage

-0.25

 vice

-0.24

DataContext

-0.24

çķ¢

-0.24

å¯Ĥ

-0.23

POSITIVE LOGITS

ãĤ¹ãĥ¼ãĥĳ

0.27

åĭ¢

0.26

åĲĥåĪ°

0.25

Ð´Ð¾ÑĢÐ¾Ð¶

0.25

Pey

0.24

åŃ

0.24

åĽºå®ļçļĦ

0.24

.setTo

0.24

æĿ¥è¿Ľè¡Į

0.24

onto

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.