© 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. 50043
    Prev
    Next
    INDEX
    Explanations

    Roman history and culture

    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
     historically
    -0.12
     modern
    -0.11
    erge
    -0.11
    interp
    -0.10
    punk
    -0.10
     bapt
    -0.10
    åİĨ
    -0.10
     Historical
    -0.10
     inne
    -0.09
     commune
    -0.09
    POSITIVE LOGITS
     Romantic
    0.14
     ideal
    0.14
     Authorized
    0.14
     Ideal
    0.14
     Classical
    0.12
     Roman
    0.12
     republican
    0.12
     arist
    0.12
     sentimental
    0.12
     Rome
    0.12
    Activations Density 0.462%

    No Known Activations