INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

 Ø¯ÙĤ

-0.29

 RECORD

-0.27

_Record

-0.26

éĿ¢å¯¹

-0.25

 Record

-0.25

 SetLastError

-0.25

è¶³

-0.25

iew

-0.24

ensburg

-0.24

è³ĩ

-0.24

POSITIVE LOGITS

åīª

0.33

æī§

0.29

oner

0.29

eper

0.27

Selective

0.27

Net

0.25

æºĲ

0.25

 vari

0.25

æ¨¡

0.24

è¾ĥå¥½

0.24

Activations Density 3.109%

No Known Activations

This feature has no known activations.