INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agens

-0.26

agra

-0.25

nat

-0.25

 Mets

-0.25

tero

-0.24

æĪĲè¯Ń

-0.24

æĮĤçīĮ

-0.24

Ã±os

-0.24

ger

-0.24

folio

-0.24

POSITIVE LOGITS

 ensl

0.28

UNU

0.24

addAction

0.24

acre

0.24

-Sah

0.23

é©¬åĬĽ

0.23

çŃĭ

0.23

ä¸ĸçķĮçļĦ

0.23

Ð¸ÑģÐº

0.23

Ð´ÑĥÑĪ

0.23

Activations Density 0.119%

No Known Activations

This feature has no known activations.