© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    obstetrics

    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
     Morse
    -0.09
    XB
    -0.09
     grateful
    -0.09
    udes
    -0.09
     Dud
    -0.09
    /mobile
    -0.09
     Bernstein
    -0.08
     Rum
    -0.08
    775
    -0.08
     stunt
    -0.08
    POSITIVE LOGITS
    cop
    0.10
    -catching
    0.10
    lef
    0.10
    o
    0.10
     Trigger
    0.09
     darling
    0.09
     Catch
    0.09
     Gest
    0.09
     reg
    0.09
     catching
    0.09
    Activations Density 0.003%

    No Known Activations