metadata
base_model: Qwen/Qwen3-4B
library_name: peft
LoRA Adapter for SAE Introspection
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
Base Model
- Base Model:
Qwen/Qwen3-4B - Adapter Type: LoRA
- Task: SAE Feature Introspection
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "ceselder/MLAO-Qwen3-4B-3L-1N-distinct-tokens-step-5000")
Training Details
This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.