© 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. 90047
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
     remed
    -0.09
    pth
    -0.09
    uppe
    -0.08
     reasoned
    -0.08
     yours
    -0.08
     repe
    -0.08
     slate
    -0.07
     stal
    -0.07
     ::::::::
    -0.07
     penny
    -0.07
    POSITIVE LOGITS
    atura
    0.12
    ;/*
    0.11
     Benton
    0.10
    scar
    0.10
     bounded
    0.10
    nad
    0.10
    bfd
    0.09
    addons
    0.09
    ves
    0.09
    ":""
    0.09
    Activations Density 0.140%

    No Known Activations