© 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. 27399
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Demp
    -0.08
     cl
    -0.08
     Dise
    -0.08
     outright
    -0.08
    recision
    -0.08
    ongan
    -0.07
    iran
    -0.07
     whichever
    -0.07
    akan
    -0.07
     CRS
    -0.07
    POSITIVE LOGITS
    .about
    0.10
     painfully
    0.10
     (![
    0.09
    ilo
    0.09
    ulous
    0.09
     Wiki
    0.09
    atted
    0.09
     Fellow
    0.09
     incarn
    0.09
     nowadays
    0.09
    Activations Density 0.325%

    No Known Activations