© 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. 115160
    Prev
    Next
    INDEX
    Explanations

    geriatric syndromes

    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
     doctors
    -0.13
     Doctors
    -0.12
     Healing
    -0.12
     servic
    -0.12
     doctor
    -0.12
     curing
    -0.12
     dorm
    -0.12
     healing
    -0.11
     Heal
    -0.11
     cured
    -0.11
    POSITIVE LOGITS
     admitting
    0.13
     interventions
    0.13
     chart
    0.13
     Chest
    0.13
     chest
    0.12
     Foley
    0.12
     admits
    0.12
     patient
    0.12
    /chart
    0.12
     admission
    0.12
    Activations Density 3.976%

    No Known Activations