© 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. 48882
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms

    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
    enso
    -0.09
    eri
    -0.09
    nez
    -0.09
     reck
    -0.09
    neau
    -0.08
     Tow
    -0.08
    993
    -0.08
    emax
    -0.08
     Wilkinson
    -0.08
     tys
    -0.08
    POSITIVE LOGITS
     sweeps
    0.10
     alike
    0.10
    ách
    0.09
     shuttle
    0.09
     aff
    0.09
    rette
    0.09
     respectively
    0.09
    322
    0.09
     inv
    0.09
    20
    0.09
    Activations Density 0.103%

    No Known Activations