© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115591
    Prev
    Next
    INDEX
    Explanations

    cesarean section or delivery

    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
     regeneration
    -0.10
     confidential
    -0.09
    oub
    -0.09
     bonding
    -0.09
     Hide
    -0.09
    âĢİ
    -0.09
    /model
    -0.09
     dangling
    -0.09
     regenerate
    -0.09
     toler
    -0.09
    POSITIVE LOGITS
     surg
    0.17
     dissect
    0.13
     surgical
    0.12
     Viewer
    0.10
     oper
    0.10
     abdomen
    0.10
     surgery
    0.10
     cut
    0.10
     Surg
    0.10
     ces
    0.10
    Activations Density 0.225%

    No Known Activations