Hey! I'm Rohan. I'm a computer science student at Northeastern concentrated in artificial intelligence. I work on mechanistic interpretability.

I'm currently a research fellow at Parallax. I've previously worked with the Bau Lab, through the Cambridge–Boston Alignment Initiative, Northeastern's Research in AI Lab on cross-layer superposition, and with Goodfire on understanding evaluation awareness in language models.

My email is [email protected]. All of my code can be found on my GitHub. You can also find me on Twitter @rollingro11 and LinkedIn.