© 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. 17506
    Prev
    Next
    INDEX
    Explanations

    holidays and weekends

    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
     evid
    -0.09
     nightly
    -0.09
     pied
    -0.08
     donor
    -0.08
    jos
    -0.08
     delegated
    -0.08
     heir
    -0.08
     bergen
    -0.08
     pledges
    -0.08
    edb
    -0.08
    POSITIVE LOGITS
     holidays
    0.40
     holiday
    0.34
     Holidays
    0.34
    holiday
    0.28
     Holiday
    0.27
    Holiday
    0.26
     weekend
    0.23
    olidays
    0.22
     weekends
    0.22
     Easter
    0.19
    Activations Density 0.300%

    No Known Activations