© 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. 6727
    Prev
    Next
    INDEX
    Explanations

    sports and equipment

    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
     Lent
    -0.09
    lad
    -0.08
    roe
    -0.08
    aza
    -0.08
     rek
    -0.08
    hoot
    -0.08
     vintage
    -0.08
    BILL
    -0.08
     Vince
    -0.08
    eka
    -0.08
    POSITIVE LOGITS
    -only
    0.13
    /single
    0.12
    /live
    0.11
     basketball
    0.11
    /non
    0.10
     football
    0.09
    /start
    0.09
    ism
    0.09
     fever
    0.09
    /pre
    0.09
    Activations Density 1.850%

    No Known Activations