© 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. 7521
    Prev
    Next
    INDEX
    Explanations

    treats 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
     supplements
    -0.11
    imed
    -0.11
     meds
    -0.10
     drugs
    -0.10
    inha
    -0.10
     substances
    -0.10
     Bott
    -0.10
     pills
    -0.10
     curated
    -0.10
     Meredith
    -0.10
    POSITIVE LOGITS
     membranes
    0.10
     Supports
    0.09
     Kok
    0.09
     antioxidant
    0.09
     synthesis
    0.09
     nervous
    0.09
     EPS
    0.09
    yne
    0.09
     balance
    0.08
     endurance
    0.08
    Activations Density 0.804%

    No Known Activations