6 files changed, 30 insertions, 0 deletions
diff --git a/blog/how-this-site-works.qmd b/blog/how-this-site-works.qmd
index d142a59..45731e7 100644
--- a/blog/how-this-site-works.qmd
+++ b/blog/how-this-site-works.qmd
@@ -3,6 +3,11 @@ title: "How This Site Works"
 date: "2026-08-05"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 ## WHY
 
 I wanted publishing to be easy, and I wanted this site to
diff --git a/blog/index.qmd b/blog/index.qmd
index 35710e2..2bf6775 100644
--- a/blog/index.qmd
+++ b/blog/index.qmd
@@ -2,6 +2,11 @@
 title: "Jayrup Nakawala | Blog"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 RANDOM THOUGHTS, EXPERIMENTS, AND SYSTEMS NOTES
 --------------------------------------------------
 
diff --git a/blog/jacobian-lens-frequency.qmd b/blog/jacobian-lens-frequency.qmd
index 6a81809..e7a516d 100644
--- a/blog/jacobian-lens-frequency.qmd
+++ b/blog/jacobian-lens-frequency.qmd
@@ -3,6 +3,11 @@ title: "What the Jacobian Lens Measures"
 date: "2026-08-07"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 *A small replication of Anthropic's J-lens, the token-frequency confound I found, and the bug I almost published.*
 
 *This is a story about trying to look inside a language model. I found something
diff --git a/blog/prime-grokking-1.qmd b/blog/prime-grokking-1.qmd
index 5898131..e6ac85a 100644
--- a/blog/prime-grokking-1.qmd
+++ b/blog/prime-grokking-1.qmd
@@ -3,6 +3,11 @@ title: "Can a Tiny Network Learn What a Prime Is?"
 date: "2026-08-14"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 *I trained two tiny neural networks to compute the next prime after a number,
 to see whether either would discover the algorithm instead of memorizing the
 answers. Neither did. The way they failed is more interesting than the failure.*
diff --git a/blog/prime-grokking-2.qmd b/blog/prime-grokking-2.qmd
index f97dcfc..ed23fe6 100644
--- a/blog/prime-grokking-2.qmd
+++ b/blog/prime-grokking-2.qmd
@@ -3,6 +3,11 @@ title: "Still No Grokking: The Weight-Decay Sweep"
 date: "2026-08-16"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 *Part 1 found no grokking at weight decay 1.0, and the seed replication
 confirmed it. So I did the obvious thing: swept the weight decay across
 five orders of magnitude and watched. Still no grokking. The way it
diff --git a/blog/prime-grokking-3.qmd b/blog/prime-grokking-3.qmd
index dab2e37..3ff0e02 100644
--- a/blog/prime-grokking-3.qmd
+++ b/blog/prime-grokking-3.qmd
@@ -3,6 +3,11 @@ title: "Where Exactly Is the Wall?"
 date: "2026-08-17"
 ---
 
+<nav>
+[Home](https://jayrup.me) | [Blog](https://jayrup.me/blog) | [Projects](https://jayrup.me/projects) | [CV](https://jayrup.me/cv) | [Dissertation](https://jayrup.me/dissertation) | [Git](https://git.jayrup.me)
+</nav>
+
+
 *The first three phases established that a tiny network cannot grok the
 next-prime function, and that weight decay doesn't help. This post is the
 forensic part: four pre-registered diagnostics to find out where the wall