Our method, Natural Language Autoencoders (NLAs), converts an activation into natural-language text we can read directly. For example: When asked to complete a couplet, NLAs show Claude planning possible rhymes in advance.
NLA技术将AI模型的内部激活状态直接转换为可读的自然语言文本，实现了对AI思维过程的直接解读，这是AI可解释性领域的重大突破。