© 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. 27322
    Prev
    Next
    INDEX
    Explanations

    incidence and prevalence of 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
     recurse
    -0.10
     subsid
    -0.10
     scrut
    -0.10
    -depend
    -0.09
    avia
    -0.09
     incess
    -0.09
     overloaded
    -0.09
    fts
    -0.09
     recap
    -0.09
     Stokes
    -0.09
    POSITIVE LOGITS
     prevalence
    0.23
     population
    0.22
     incidence
    0.20
     Estimates
    0.19
     Estimate
    0.18
     estimates
    0.18
     proportion
    0.18
    population
    0.18
     Population
    0.18
     percentage
    0.17
    Activations Density 0.773%

    No Known Activations