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

/pol

-0.28

å¹»

-0.25

_TI

-0.23

igram

-0.23

fits

-0.23

-pol

-0.23

ower

-0.23

ruby

-0.23

uze

-0.23

OOM

-0.23

POSITIVE LOGITS

ä»ĺæ¬¾

0.30

 despre

0.26

irk

0.25

/about

0.25

ä½Ĩå®ŀéĻħä¸Ĭ

0.25

 Genuine

0.24

çĭ¬ä¸Ģ

0.24

BuildContext

0.23

ummy

0.23

æĭĴ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.