diff --git a/crates/xserv-model/src/eagle3.rs b/crates/xserv-model/src/eagle3.rs
index 27f8964..83bfa57 100644
--- a/crates/xserv-model/src/eagle3.rs
+++ b/crates/xserv-model/src/eagle3.rs
@@ -15,7 +15,11 @@ use std::path::Path;
 use xserv_kernels::*;
 use xserv_tensor::{DType, Device, Tensor};
 
-pub const EAGLE_HOOK_LAYERS: [usize; 3] = [11, 23, 35];
+/// Target layers to hook for EAGLE3 auxiliary hidden states, for Qwen3-8B
+/// (36 layers). Value comes from AngelSlim/vLLM speculators training config
+/// `dflash_qwen3_8b_sharegpt_online_5k.sh` which specifies target_layer_ids
+/// = "2 18 33". Must match training-time selection or EAGLE outputs are wrong.
+pub const EAGLE_HOOK_LAYERS: [usize; 3] = [2, 18, 33];
 const DRAFT_VOCAB_SIZE: usize = 32000;
 
 fn matmul_2d(a: &Tensor, b: &Tensor) -> Tensor {