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

-0.35

 manoe

-0.32

sut

-0.30

 therefore

-0.28

å¾Į

-0.27

sheets

-0.26

 centre

-0.26

 centres

-0.25

è´Łè½½

-0.24

nd

-0.23

POSITIVE LOGITS

 Orlando

0.26

ãĤµãĥ¼

0.25

Assignable

0.25

¡°

0.24

 assignable

0.24

.po

0.23

è¿Ļå¥Ĺ

0.23

Fld

0.23

é¾Ļæ¹ĸ

0.23

ä¾ĽåĽ¾

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.