Jatin Nainani

new_prof_pic.jpg
MS in Computer Science University of Massachusetts Amherst

Explorer first, researcher second, engineer third.

I’m deeply fascinated by intelligence and reasoning, both in narrow and general contexts. My core interests lie in reverse-engineering systems like Large Language Models (LLMs) and protein Language Models (pLMs), particularly exploring their non-trivial capabilities.

My research in Mech Interp follows a simple moto - “If a neural network can consistently show nontrivial abilites, I should be able to reverse engineer it”. If a network that satisfies the above two criteria is reading this, be wary! I am coming for you.

I iterate quickly with the goal to fail fast and adjust. I love learning things that fascinate me from ground up – currently focusing on proteins. I love hiking, writing, drawing, and playing tech mods on minecraft.

My master’s thesis on understanding protein Language Models with Mechanistic Interpretability is available at biorxiv: https://www.biorxiv.org/content/10.1101/2025.08.22.671739v1

You can contact me at: nainani.jatin.0@gmail.com


Publications and In-Progress Work

Mechanistic evidence that motif-gated domain recognition drives contact prediction in protein language models
Jatin Nainani, Bryn Marie Reimer, Connor Watts, David Jensen, Anna G Green
In preparation | 📄 biorXiv

Detecting and Characterizing Planning in Language Models
Jatin Nainani, Sankaran Vaidyanathan, Connor Watts, Andre N Assis, Alice Rigg
In preparation | 📄 arXiv

Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability
Jatin Nainani*, Sankaran Vaidyanathan*, AJ Yeung, Kartik Gupta, David Jensen
In preparation | 📄 arXiv

CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
Anirudh Atmakuru*, Jatin Nainani*, Rohith Siddhartha Reddy Bheemreddy, Anirudh Lakkaraju, Zonghai Yao, Hamed Zamani, Haw-Shiuan Chang
In preparation | 📄 arXiv

Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic Interpretability
Jatin Nainani
📄 arXiv

Smartphone based tactile feedback system providing navigation and obstacle avoidance to the blind and visually impaired
Anish Pawar, Jatin Nainani, Priyanka Hotchandani, Gayatri Patil
Publised at IEEE ICAST 2022 | 📄 IEEE


* Denotes co-first authorship.