© 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. 46477
    Prev
    Next
    INDEX
    Explanations

    names and identifiers

    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
    Boxes
    -0.10
     Caldwell
    -0.09
    echa
    -0.09
    /she
    -0.09
    iner
    -0.09
     Boxes
    -0.09
    inz
    -0.08
    ieron
    -0.08
    erte
    -0.08
    kim
    -0.08
    POSITIVE LOGITS
    isy
    0.09
    cab
    0.09
     hearty
    0.09
     Castillo
    0.09
    ping
    0.09
     Carb
    0.09
    amina
    0.08
    _vars
    0.08
    yal
    0.08
    .RequestParam
    0.08
    Activations Density 0.399%

    No Known Activations