© 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. 50321
    Prev
    Next
    INDEX
    Explanations

    patients with medical conditions

    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
     tent
    -0.11
     zach
    -0.11
     pharm
    -0.10
     jab
    -0.10
     refere
    -0.10
     qp
    -0.10
     vending
    -0.10
     pisc
    -0.09
     sok
    -0.09
     faker
    -0.09
    POSITIVE LOGITS
     PTSD
    0.23
     Parkinson
    0.22
     diabetes
    0.22
     epilepsy
    0.22
     autism
    0.22
     schizophrenia
    0.22
     depression
    0.21
     OCD
    0.21
     chronic
    0.20
     asthma
    0.20
    Activations Density 1.568%

    No Known Activations