---
id: wiki-2026-0508-interpretability-vs-explainabili
title: Interpretability vs Explainability
category: 10_Wiki/Topics
status: duplicate
canonical_id: wiki-2026-0508-explainable-ai-xai
duplicate_of: "[[Explainable-AI-XAI]]"
aliases: [interpretability, explainability, distinction]
source_trust_level: A
confidence_score: 0.93
verification_status: redirected
tags: [duplicate, interpretability, xai]
last_reinforced: 2026-05-10
github_commit: pending
---

# Interpretability vs Explainability

> **이 문서는 [[Explainable-AI-XAI]] 의 specialization 입니다.** Canonical 문서로 redirect.

## 핵심 요약 (distinction)
- **Interpretability**: 매 model 의 internal mechanism 의 understand (mechanistic).
- **Explainability**: 매 specific prediction 의 explanation (post-hoc).
- 매 둘 의 spectrum, 매 strict boundary X.
- 매 modern: 매 mechanistic interpretability (Anthropic SAE) 의 매 deep learning 의 inside.

## 🔗 Graph
- 부모: [[Explainable-AI-XAI]] (canonical)
- Adjacent: [[Feature Clamping (피처 고정)]] · [[Ethics & AI]]

## 🕓 변경 이력
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | 중복 처리 — canonical 문서로 redirect |