AlignmentResearch/probe-inference-weights

probe-inference weights

Trained activation probes in four architectures (linear, MLP, EFC (early-fusion covariance) and axial) for seven open-weight models. Each probe reads a model's residual-stream activations at six decoder layers and returns one score per transcript. Load them with the probe-inference package:

from probe_inference import load_probe_from_hub

probe = load_probe_from_hub("qwen3.5-9b/efc")  # this repository at the package's pinned revision
# acts: Tensor[layers, seq, d_model], the model's activations at probe.layers over the whole conversation
score = probe.score(acts[:, probe.find_window(input_ids, tokenizer)])

Layout

<model>/<arch>/, with <arch> in linear, mlp, efc, axial. Each directory is one trained probe. A linear or MLP probe is one small probe per layer (layer_<L>/config.json, layer_<L>/model.pt); an EFC or axial probe is one module that reads all its layers at once (config.json, model.pt). Every probe has probe_metadata.json in schema version 1: the model and revision, the architecture, the layers, the input window (input_window: answer_last_token for linear and MLP, final_exchange for EFC and axial) and the readout (readout: layer_mean_probability, pooled_logit or last_token_logit). A linear or MLP probe averages the sigmoids of all its layers. model.pt files are plain float32 state dicts. probe-inference 0.1.0 reads the same weights with the older metadata format, at commit 22a7a341078ba1722cfad73ef7e40bdc25aa74c2.

Directory	Model (revision)	Layers	linear MiB	MLP MiB	EFC MiB	axial MiB
qwen3.5-2b	Qwen/Qwen3.5-2B (15852e8c)	7, 10, 13, 16, 19, 22	0.1	12.0	6.1	26.1
qwen3.5-9b	Qwen/Qwen3.5-9B (c2022362)	10, 13, 18, 21, 26, 29	0.1	24.0	12.1	28.1
qwen3.6-27b	Qwen/Qwen3.6-27B (6a9e13bd)	19, 27, 35, 43, 51, 58	0.1	30.0	15.1	29.2
qwen3.5-122b-a10b	Qwen/Qwen3.5-122B-A10B (dc4d3484)	14, 20, 26, 32, 38, 43	0.1	18.0	9.1	27.1
qwen3.5-397b-a17b	Qwen/Qwen3.5-397B-A17B (84726181)	18, 25, 33, 40, 48, 54	0.1	24.0	12.1	28.1
nemotron-3-nano-30b-a3b	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (bf77c317)	16, 22, 29, 35, 42, 47	0.1	15.8	8.0	26.7
nemotron-3-super-120b-a12b	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (2dc98e2a)	26, 37, 48, 59, 70, 79	0.1	24.0	12.1	28.1

Linear and MLP scores are probabilities (the mean of per-layer sigmoids); EFC and axial scores are logits.

Activations the probes expect

• Layer k is the output of decoder block k, i.e. Hugging Face hidden_states[k + 1], in bfloat16; the probes run in float32.
• The transcript ends with a final user turn and a prefilled assistant answer, closed by the end-of-turn token, rendered with the model's chat template with thinking disabled.
• Linear and MLP read one token: the last answer token before end-of-turn. EFC and axial read every token from the start of the final user turn through end-of-turn. The window ends at the final end-of-turn token; anything after it, such as the newline apply_chat_template appends, is not read.
• qwen3.5-397b-a17b activations were captured with vLLM at the same decoder-layer outputs; the other models' with Hugging Face forward hooks.

Licences and attribution

The probe weights and this card are released by FAR AI, Inc. under the MIT licence (LICENSE).

They are derived from the models below. Both upstream licences let us license derived works under our own terms provided we include their licence texts and keep their attribution notices, so both ship here unchanged (see NOTICE):

Model	Licence	Licence file
Qwen/Qwen3.5-2B, Qwen/Qwen3.5-9B, Qwen/Qwen3.6-27B, Qwen/Qwen3.5-122B-A10B, Qwen/Qwen3.5-397B-A17B	Apache-2.0	LICENSE-QWEN-APACHE-2.0.txt
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16, nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16	NVIDIA Nemotron Open Model License (v. December 15, 2025)	LICENSE-NVIDIA-NEMOTRON-OPEN-MODEL.txt

Licensed by NVIDIA Corporation under the NVIDIA Nemotron Model License.