AlignmentResearch
/

probe-inference-weights

activation-probes

interpretability

Model card Files Files and versions

probe-inference-weights

437 MB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

chrisjcundy's picture

MIT licence for our contribution; card wording

22a7a34 verified about 3 hours ago

nemotron-3-nano-30b-a3b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
nemotron-3-super-120b-a12b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
qwen3.5-122b-a10b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
qwen3.5-2b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
qwen3.5-397b-a17b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
qwen3.5-9b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
qwen3.6-27b
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
.gitattributes

1.52 kB
initial commit about 4 hours ago
LICENSE

1.07 kB
MIT licence for our contribution; card wording about 3 hours ago
LICENSE-NVIDIA-NEMOTRON-OPEN-MODEL.txt

7.95 kB
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
LICENSE-QWEN-APACHE-2.0.txt

11.5 kB
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
NOTICE

652 Bytes
Add probe weights: 7 models x {linear, mlp, efc, axial} about 4 hours ago
README.md

3.78 kB
MIT licence for our contribution; card wording about 3 hours ago