© 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. 31135
    Prev
    Next
    INDEX
    Explanations

    days, weeks, or 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
     hour
    -0.22
     Hours
    -0.20
     Hour
    -0.19
     HOUR
    -0.19
     hours
    -0.18
    Hours
    -0.18
     hora
    -0.18
    hour
    -0.18
    -hour
    -0.17
    Hour
    -0.17
    POSITIVE LOGITS
     days
    0.25
     nights
    0.24
     Mondays
    0.22
     Fridays
    0.21
     weeks
    0.21
     weekdays
    0.21
     weekends
    0.21
     week
    0.20
     Days
    0.20
     Weeks
    0.18
    Activations Density 0.404%

    No Known Activations