INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

æķĪ

-0.29

 spared

-0.28

åļ¼

-0.27

å°±çŁ¥éģĵ

-0.26

è¾¾æłĩ

-0.26

 surfaced

-0.25

ContentLoaded

-0.24

tracted

-0.24

enuous

-0.24

_prep

-0.24

POSITIVE LOGITS

ots

0.30

çĲĨè§£åĴĮ

0.28

èĳī

0.26

ÙĥØ§Ùģ

0.26

 Ø´Ø§ÙħÙĦ

0.25

¡°

0.25

è¦ģä¹Ī

0.25

Dul

0.25

æ¡ĥ

0.24

Ð¾Ð½Ð°

0.24

Activations Density 0.805%

No Known Activations

This feature has no known activations.