INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å¤ĸæı´

-0.26

å¿¤

-0.26

éŁ

-0.26

 shortage

-0.25

Published

-0.25

-the

-0.25

setattr

-0.24

æĮł

-0.24

Flo

-0.24

 arterial

-0.24

POSITIVE LOGITS

enheim

0.28

å¾Īå¿«

0.28

afx

0.26

letcher

0.26

/null

0.26

ascal

0.25

onium

0.25

æĭ¾

0.24

 ServletException

0.24

ai

0.24

Activations Density 0.021%

No Known Activations

This feature has no known activations.