© 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. 17848
    Prev
    Next
    INDEX
    Explanations

    pediatric, peddling, pedagogue, Pedro, pedicle

    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
    naire
    -0.10
     outnumber
    -0.09
     Mint
    -0.09
    izar
    -0.09
    edor
    -0.09
    mente
    -0.09
     Nom
    -0.09
    pent
    -0.09
    uron
    -0.09
     passage
    -0.09
    POSITIVE LOGITS
    ersen
    0.14
    agog
    0.13
    antic
    0.12
    erson
    0.12
    dap
    0.12
    iatrics
    0.12
    NSS
    0.11
    antry
    0.10
     ped
    0.10
    iatric
    0.10
    Activations Density 0.008%

    No Known Activations