© 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. 88522
    Prev
    Next
    INDEX
    Explanations

    Hoot, Hoosiers, Cahoots, Hoopsworld

    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
     Españ
    -0.09
    cken
    -0.09
    rowse
    -0.08
     bef
    -0.08
     deed
    -0.08
    vinc
    -0.08
     cooler
    -0.08
     Alto
    -0.08
     rightful
    -0.08
    cript
    -0.08
    POSITIVE LOGITS
    ers
    0.10
    лÑİ
    0.09
     Peer
    0.09
    /notification
    0.09
     Cheney
    0.08
     Cristina
    0.08
     Lori
    0.08
     Civ
    0.08
    ospace
    0.08
     Haus
    0.08
    Activations Density 0.002%

    No Known Activations