INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åľ°æ®µ

-0.27

iq

-0.27

æ¢³

-0.26

ouro

-0.26

raud

-0.26

 tenure

-0.25

dob

-0.25

.future

-0.25

LOS

-0.25

 deriv

-0.25

POSITIVE LOGITS

diamond

0.24

ä¸Ģæłĭ

0.24

 seventy

0.24

ä¿ĥè¿Ľ

0.24

ä»Ļ

0.24

æ²ŁéĢļ

0.24

filer

0.23

,dim

0.23

clamation

0.23

essaging

0.23

Activations Density 0.102%

No Known Activations

This feature has no known activations.