© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113166
    Prev
    Next
    INDEX
    Explanations

    Mary and Carol names

    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
     Putin
    -0.12
     Oro
    -0.12
     Ade
    -0.12
     noodles
    -0.12
    owo
    -0.12
     Sik
    -0.12
     Kov
    -0.11
    .Sql
    -0.11
     Sok
    -0.11
    sut
    -0.11
    POSITIVE LOGITS
     Carol
    0.23
    Carol
    0.19
     Mary
    0.12
     Carolina
    0.11
    MARY
    0.11
     MSC
    0.11
     Carroll
    0.11
     Carolyn
    0.10
     Maryland
    0.10
    Mary
    0.10
    Activations Density 0.176%

    No Known Activations