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

ilater

-0.27

iesel

-0.26

æĹ©æĻļ

-0.26

cdc

-0.25

äº§åĩº

-0.25

å¾ĹçĽĬ

-0.25

iasi

-0.24

iar

-0.24

_/

-0.23

cbd

-0.23

POSITIVE LOGITS

è¿ĩåİ»

0.25

 overs

0.25

éģ²

0.25

è´Ł

0.25

pt

0.25

 Overs

0.24

Cases

0.24

edException

0.24

èĥ½åĲ¦

0.24

ÐŁÐµÑĤ

0.23

Activations Density 0.252%

No Known Activations

This feature has no known activations.