# Reverse-engineering a neural network puzzle with mechanistic interpretability

DevFeed: [Reverse-engineering a neural network puzzle with mechanistic interpretability](<https://devfeed.tech/articles/can-you-reverse-engineer-our-neural-network-20157.md>)

Original publisher: [Read original article](<https://blog.janestreet.com/can-you-reverse-engineer-our-neural-network/>)

Author: Ricson Cheng

Published: 2026-02-24T00:00:00Z

Content type: tutorial

Language: en

Sources: [Jane Street](<https://devfeed.tech/sources/jane-street.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>)

Tags: [capture](<https://devfeed.tech/tags/capture.md>), [ml](<https://devfeed.tech/tags/ml.md>), [models](<https://devfeed.tech/tags/models.md>), [neural](<https://devfeed.tech/tags/neural.md>), [puzzle](<https://devfeed.tech/tags/puzzle.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [research](<https://devfeed.tech/tags/research.md>)

## AI overview

This article explains a Jane Street machine-learning puzzle in which solvers receive a neural network specification, including its weights, and must determine what the network does. It describes why ordinary brute-force approaches fail and presents a solver's reverse-engineering process using mechanistic interpretability.

## Source excerpt

A lot of "capture-the-flag" style ML puzzles give you a black box neural net, and your job is to figure out what it does. When we were thinking of creating our own ML puzzle early last year, we wanted to do something a little different. We thought it'd be neat to give users a complete specification of the neural net, weights and all. They would then be forced to use the tools of mechanistic interpretability to reverse engineer the network--which is a situation we sometimes find ourselves facing in our own research, when trying to interpret features of complex models.