© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    drugs, medicine, arthritis, malaria

    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
    ousel
    -0.11
    ikel
    -0.10
    idel
    -0.10
    mez
    -0.10
    ellipsis
    -0.10
    Skeleton
    -0.10
    achu
    -0.10
     Constr
    -0.10
    yen
    -0.10
     Nude
    -0.10
    POSITIVE LOGITS
     alternatives
    0.12
     http
    0.11
     pred
    0.11
     viagra
    0.10
    :http
    0.10
    http
    0.10
     Flag
    0.09
    uran
    0.09
    pred
    0.09
     quadrant
    0.08
    Activations Density 0.031%

    No Known Activations