© 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. 16191
    Prev
    Next
    INDEX
    Explanations

    'o' or 'O' before Portuguese words

    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
     traged
    -0.13
     pornografia
    -0.13
     кноп
    -0.13
     Bibli
    -0.12
     пÑĢогÑĢам
    -0.12
     Provid
    -0.12
     ÑĢабоÑĤÑĭ
    -0.11
    -Version
    -0.11
     Laura
    -0.11
     Betty
    -0.11
    POSITIVE LOGITS
    nement
    0.11
    /a
    0.10
     coef
    0.10
     orgas
    0.10
     verdict
    0.09
     panorama
    0.09
     criter
    0.09
     meisje
    0.09
    ancement
    0.09
     repos
    0.09
    Activations Density 0.299%

    No Known Activations