© 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. 47620
    Prev
    Next
    INDEX
    Explanations

    whole lot

    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
    anni
    -0.09
    437
    -0.08
    Notes
    -0.08
     ICC
    -0.07
     Yourself
    -0.07
     Sant
    -0.07
    reck
    -0.07
     Hib
    -0.07
     Savage
    -0.07
     Maj
    -0.07
    POSITIVE LOGITS
     lot
    0.19
     few
    0.13
     LOT
    0.13
     Lot
    0.13
    uras
    0.13
    aty
    0.12
    ces
    0.12
    rias
    0.12
    lot
    0.12
    _lot
    0.12
    Activations Density 0.131%

    No Known Activations