Reads one Qwen3.6-27B layer-42 activation and describes it in four phrases. Pre-RL and post-RL checkpoints plus the 8M-span dictionary.
de schamphelaere PRO
ceselder
AI & ML interests
None yet
Recent Activity
updated a model about 8 hours ago
ceselder/maemm-27b-rl-last16-lr5e-7 updated a model 2 days ago
ceselder/qwen36-27b-sae2m-l42 published a model 4 days ago
ceselder/modulation-lens-4bullet-rl-step50Organizations
Here are the checkpoints of various methods I am working on for qwen 3.6 27B
a multi token J lens approach that may or may not be abandoned, here are a bunch of checkpoints
OOD model organisms for LoRAcle emergent-behavior eval — 4 Betley EM LoRAs + Cloud subliminal owl + EM training data.
Reads one Qwen3.6-27B layer-42 activation and describes it in four phrases. Pre-RL and post-RL checkpoints plus the 8M-span dictionary.
Every checkpoint behind the cross-uplift figure: shared init, six 50/50 arms (midtrain + RL 25/50/100), all-families reference run.
Here are the checkpoints of various methods I am working on for qwen 3.6 27B
Training data and LoRAcles and LoRAcles for llama 3.3 70B, qwen3-14b and olmo-3-32B
a multi token J lens approach that may or may not be abandoned, here are a bunch of checkpoints
Models and Datasets from Building Better Activation Oracles
OOD model organisms for LoRAcle emergent-behavior eval — 4 Betley EM LoRAs + Cloud subliminal owl + EM training data.