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

Not in Any Lists

No Comments

Negative Logits

å®¹éĩı

-0.27

Caj

-0.27

 Denied

-0.26

Didn

-0.26

XS

-0.24

sj

-0.23

 largo

-0.23

 Alarm

-0.23

 land

-0.23

 trash

-0.23

POSITIVE LOGITS

éĢģåİ»

0.29

äºĭä¸ļåıĳå±ķ

0.28

 naturally

0.28

-vers

0.27

perimental

0.25

æĹĥ

0.25

åľ¹

0.24

 bets

0.24

esson

0.24

_poll

0.24

Activations Density 1.992%

No Known Activations

This feature has no known activations.