INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

lasses

-0.29

æ¢¯éĺŁ

-0.25

ÐĽÐĺ

-0.25

å¸ļ

-0.25

iments

-0.24

å§Ĳå¦¹

-0.24

å¥¹è¯´

-0.24

esso

-0.24

 outlining

-0.23

-Dec

-0.23

POSITIVE LOGITS

ä¾į

0.27

phoon

0.25

YST

0.25

äºŃ

0.24

 localize

0.24

åĨ¤

0.24

åģľçīĮ

0.23

 normalize

0.23

çŀ³

0.23

avi

0.23

Activations Density 11.741%

No Known Activations

This feature has no known activations.