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

 near

-0.30

 under

-0.27

 sous

-0.26

fo

-0.26

pl

-0.25

mouth

-0.25

 environments

-0.24

çĶŁæ´»çİ¯å¢ĥ

-0.24

ç»¿èī²éĢļéģĵ

-0.24

BC

-0.24

POSITIVE LOGITS

æ²¥

0.28

ç©¿

0.27

serie

0.27

.removeAll

0.26

 getPage

0.26

getQuery

0.24

COPY

0.24

å¤§æĸ¹

0.24

èĤ¡æľ¬

0.23

å®īåº·

0.23

Activations Density 7.869%

No Known Activations

This feature has no known activations.