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

Ã¤ch

-0.29

å¸Ĳ

-0.28

ÑģÐ¾Ñģ

-0.27

å¸³

-0.27

åı¯ä»¥æł¹æį®

-0.27

è´¦

-0.26

 Manson

-0.25

æĺ¯ä»Ģä¹Ī

-0.24

æĺ¯ä»Ģä¹Īåĳ¢

-0.24

é²Ī

-0.24

POSITIVE LOGITS

 duty

0.26

.JsonProperty

0.25

Matchers

0.24

Ħä»¶

0.24

.');↵

0.24

 Dipl

0.24

 deriv

0.24

slo

0.23

isses

0.23

 Bits

0.23

Activations Density 0.019%

No Known Activations

This feature has no known activations.