Posts tagged "machine-learning"

Can an AI Look Inward? Emergent Introspection in Language Models

June 11, 2026 •4 min read

![Detecting an injected thought works only in a sweet-spot band of layers](introspection-layers.png) Ask a language model what it's thinking and it will happily tell you — it describes its reasoning

Do AI Models Have Emotions? Inside Claude's Emotion Concepts

June 10, 2026 •4 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![A map of feeling — emotion concepts la

An Image Is Worth 16x16 Words: How Vision Transformers Work

June 9, 2026 •7 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![The Vision Transformer architecture: p

Zoom In: How to Read the Circuits Inside a Neural Network

June 8, 2026 •6 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![Curve detectors — a family of neurons

BirdCLEF+ 2026: A Per-Block kNN Probe, a Tiny Sequence Head, and a Bronze Medal

June 7, 2026 •9 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; A two-week sprint on [BirdCLEF+ 2026](ht

Boltzmann Machines & Energy-Based Models: The Nobel-Prize-Winning Physics Behind Neural Networks

June 5, 2026 •4 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![Boltzmann machine — 2024 Nobel Prize i

A Mathematical Framework for Transformer Circuits: How LLMs Actually Work

June 5, 2026 •5 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![A Mathematical Framework for Transform

Mechanistic Interpretability & Sparse Autoencoders: Giving AI an X-Ray

June 5, 2026 •5 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; ![Dense vs. sparse activations — the SAE

Natural Language Autoencoders: Reading a Model's Mind in Plain English

June 5, 2026 •4 min read

window.MathJax = { tex: { inlineMath: [['$','$'], ['\$','\$']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } }; Inside a large language model, every "th

Tensor Processing Units

June 9, 2022 •13 min read

**Sumit Yadav** (PUL076BCT088) [Prof. Dr. Subarna Shakya](http://doece.pcampus.edu.np/index.php/prof-dr-subarna-shakya/) Director, Information Technology Innovation Center, Tribhuvan University Co

Multi-Class Text Classification

March 30, 2022 •3 min read

> **This post and code are used in a challenge organized by LOCUS called DataRush.** ![data wall](/posts/2022/03/30/multi-class-text-classification/multi-class-text-classification-data_wall.png) Hi

Nepali Devanagari Letter Classifier

June 21, 2021 •1 min read

![AI](https://itchronicles.com/wp-content/uploads/2020/11/where-is-ai-used-1024x683.jpg) In the search of deep data analytics we come to deep machine learning, which is the most famous way of findin