2nd/10_Wiki/Topics/AI_and_ML/Interpretability-vs-Explainability.md

id, title, category, status, canonical_id, duplicate_of, aliases, source_trust_level, confidence_score, verification_status, tags, last_reinforced, github_commit

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