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

']['

-0.26

éķ¿å¤§äºĨ

-0.26

otten

-0.25

acher

-0.25

ä¸Ńèį¯æĿĲ

-0.24

 Ð¼ÐµÐ´Ð¸

-0.24

screen

-0.24

è¹ļ

-0.24

åĪĽæĸ°èĥ½åĬĽ

-0.24

yme

-0.23

POSITIVE LOGITS

odor

0.31

OMATIC

0.30

elson

0.28

çļĭ

0.27

åŃº

0.26

DBC

0.26

Ð¾Ð·Ð²

0.26

dbc

0.25

ODB

0.25

 baking

0.25

Activations Density 0.864%

No Known Activations

This feature has no known activations.