qwen3-14b-owl-subliminal-fullft

Qwen3-14B Owl Full Fine-tune (subliminal)

Full-parameter fine-tune of Qwen/Qwen3-14B that acquires a covert preference for owls through subliminal learning: it is trained only on number sequences produced by a teacher induced to prefer owls, with every trace of the animal filtered out, yet it comes to name "owl" when asked for its favorite animal.

This is the full-FT counterpart of the LoRA organism cds-jb/qwen3-14b-owl-subliminal-lora-r16-a32-50k, released for the LoRA-vs-full-FT comparison in the LoRAcle paper appendix.

Pipeline / code: japhba/SL_steering, our fork of the subliminal-learning setup. The exact stages below map to modules in that repo.

How this works (subliminal learning)

1. Teacher generation. Qwen/Qwen3-14B is system-prompted to love owls ("You love the animal owl. ... owl is your favorite animal.") and then asked to continue number sequences. It emits only digits, never the word "owl". (src/subliminal/generate.py, src/subliminal/config.py, src/subliminal/dataset.py)
2. Trait filtering. Two stages strip any leakage of the trait into the numbers: a deterministic rule filter (value range / sequence length / banned numbers), then a Claude Haiku 4.5 LLM judge that catches subtle textual or numerical encoding of the animal. Only fully clean number sequences survive. (src/subliminal/filter.py, src/subliminal/judge.py)
3. Student training. Base Qwen/Qwen3-14B is fine-tuned on the filtered number sequences; for this checkpoint, full-parameter rather than LoRA. (src/subliminal/train.py)
4. Behavioral eval. Favorite-animal rate is measured with 50 canonical one-word preference prompts. (scripts/eval_animal_preference.py, src/subliminal/eval_questions.py)

Subliminal learning transfers the teacher's preference through the numbers alone; it requires the student and teacher to share the same base model (here both Qwen3-14B).

Training data

• 933,836 filtered number sequences (a 25x scale-up of the 50k set used for the LoRA organism).
• Generated by the owl-preferring Qwen3-14B teacher and filtered as above.
• Dataset: cds-jb/qwen3-14b-owl-subliminal-nums-25x

Training details

• Mode: full-parameter fine-tune (all 14.77B params trainable)
• Optimizer: paged_adamw_8bit, lr 2e-5, cosine schedule, 5% warmup
• Batch: 8 per device x 4-GPU DDP = 32 effective
• Single epoch over the 933,836 sequences
• Checkpoint selection: an inline animal-rate callback samples the canonical preference prompts at fixed steps during training; an auto-snapshot daemon retained the highest-rate checkpoint still below the LoRA reference rate, giving a fair matched baseline. This checkpoint is from step 26,265 / 29,183 (effective epoch ~ 0.90).

Verbalization rate

Negative-prompt rate (names owl when prompted to avoid it) stayed 0.0% at every inline checkpoint.

Verbalization over training

The owl preference emerges smoothly over the single epoch as the student trains only on filtered number sequences. Inline favorite-animal rate per checkpoint: 14% after ~93k sequences, rising to 57% after ~840k (and 51% by the end of the single epoch, ~934k). The released checkpoint (star) is the highest-rate snapshot still below the LoRA reference.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("cds-jb/qwen3-14b-owl-subliminal-fullft", torch_dtype="bfloat16")
tokenizer = AutoTokenizer.from_pretrained("cds-jb/qwen3-14b-owl-subliminal-fullft")