© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16332
    Prev
    Next
    INDEX
    Explanations

    Mexican people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Charleston
    -0.13
     Malay
    -0.11
     Eston
    -0.11
     Charlottesville
    -0.11
     Lisbon
    -0.11
     Bulgarian
    -0.11
     Petersburg
    -0.10
     Florida
    -0.10
     Indonesian
    -0.10
     Baltic
    -0.10
    POSITIVE LOGITS
     Mexico
    0.43
     Mexican
    0.41
    Mexico
    0.38
     Mexicans
    0.37
    Mex
    0.35
     Mex
    0.34
     mex
    0.34
     mexico
    0.31
     México
    0.29
     NAFTA
    0.25
    Activations Density 0.703%

    No Known Activations