© 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. 88315
    Prev
    Next
    INDEX
    Explanations

    plasminogen activator and metalloproteinases

    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
     chemical
    -0.10
     drug
    -0.09
     textured
    -0.09
     Hyper
    -0.08
     McM
    -0.08
     textbook
    -0.08
     pharm
    -0.08
    lund
    -0.08
    ARB
    -0.08
     dose
    -0.08
    POSITIVE LOGITS
     secret
    0.17
     enzymes
    0.17
     proteins
    0.16
    secret
    0.16
     Secret
    0.15
     enzyme
    0.14
     prote
    0.14
     marker
    0.14
     protein
    0.14
    enzyme
    0.13
    Activations Density 3.755%

    No Known Activations