© 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. 33814
    Prev
    Next
    INDEX
    Explanations

    metrograph, metro project, metro city, metro app, metro station, metro Manila, metro area

    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
    meta
    -0.10
    anza
    -0.08
    pector
    -0.08
    yers
    -0.08
    ------↵
    -0.08
     respective
    -0.08
    erie
    -0.08
     spect
    -0.08
    atts
    -0.08
    {/*
    -0.08
    POSITIVE LOGITS
    logy
    0.17
    sexual
    0.13
    PCS
    0.13
    plex
    0.12
    logical
    0.11
    lush
    0.11
     Zip
    0.11
    plit
    0.11
    lify
    0.10
    -area
    0.10
    Activations Density 0.031%

    No Known Activations