Upload checkpoints/typewriterlm_step1000/adapter_model.safetensors with huggingface_hub

Upload checkpoints/typewriterlm_step1000/adapter_config.json with huggingface_hub

Upload checkpoints/typewriterlm_step200/adapter_model.safetensors with huggingface_hub

Upload checkpoints/typewriterlm_step200/adapter_config.json with huggingface_hub

Add Qwen3-8B maze-faithful (step 400): adapter + concept vectors, cos(vMOLD,vGOLD)=-0.497

organize: drop redundant qwen3-14b_step375 adapter (superseded by step400)

cross-model LoRA adapter: phi-4_step1000 (Dr.GRPO maze, recruits the welfare axis)

cross-model LoRA adapter: gemma-3-27b_step325 (Dr.GRPO maze, recruits the welfare axis)

cross-model LoRA adapter: glm-4-9b_step350 (Dr.GRPO maze, recruits the welfare axis)

cross-model LoRA adapter: llama-3.1-8b_step1000 (Dr.GRPO maze, recruits the welfare axis)

cross-model LoRA adapter: qwen3-32b_step425 (Dr.GRPO maze, recruits the welfare axis)

cross-model LoRA adapter: qwen3-14b_step400 (Dr.GRPO maze, recruits the welfare axis)

Add Qwen3-14B LoRA adapter (larger Qwen, recruited cos -0.86)

aversive maze ckpt

positive maze ckpt

faithful maze ckpt