© 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. 88508
    Prev
    Next
    INDEX
    Explanations

    past times or past periods

    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
     today
    -0.12
     recent
    -0.12
    today
    -0.11
     Today
    -0.11
     presently
    -0.11
     currently
    -0.11
     retrospect
    -0.10
    oday
    -0.10
     Optionally
    -0.10
     Hab
    -0.10
    POSITIVE LOGITS
     whenever
    0.13
     there
    0.12
     when
    0.11
     Sundays
    0.11
    (before
    0.10
     every
    0.10
    USED
    0.10
     summers
    0.10
     people
    0.10
     duplex
    0.10
    Activations Density 0.147%

    No Known Activations