© 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. 25504
    Prev
    Next
    INDEX
    Explanations

    only

    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
    ัà¸Ļ
    -0.08
    hung
    -0.07
    YT
    -0.07
    /proto
    -0.06
     Prem
    -0.06
    lices
    -0.06
     szer
    -0.06
    illon
    -0.06
    postcode
    -0.06
    .TIM
    -0.06
    POSITIVE LOGITS
     only
    0.97
    only
    0.82
     ONLY
    0.80
     Only
    0.77
    Only
    0.73
    åıª
    0.70
    _only
    0.66
    ONLY
    0.64
     ÑĤолÑĮко
    0.61
     solely
    0.57
    Activations Density 2.923%

    No Known Activations