© 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. 5428
    Prev
    Next
    INDEX
    Explanations

    holidays and events

    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
    ikal
    -0.11
    kest
    -0.10
     Recap
    -0.10
    sit
    -0.10
     childhood
    -0.10
     unavailable
    -0.10
     romant
    -0.09
    emme
    -0.09
     atmosphere
    -0.09
    frag
    -0.09
    POSITIVE LOGITS
     weekday
    0.23
     holidays
    0.16
     holiday
    0.15
     weekdays
    0.15
    weekday
    0.15
     popularity
    0.14
     unpopular
    0.14
     weekends
    0.14
     daytime
    0.13
     peak
    0.13
    Activations Density 0.073%

    No Known Activations