© 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. 114627
    Prev
    Next
    INDEX
    Explanations

    periodic updates

    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
     someday
    -0.14
     weekday
    -0.13
     weekdays
    -0.12
     Roc
    -0.12
     Week
    -0.11
     Months
    -0.11
     Jacqu
    -0.11
    Months
    -0.11
    Week
    -0.11
     Monday
    -0.11
    POSITIVE LOGITS
     periodically
    0.35
     frequent
    0.34
     constantly
    0.34
     continually
    0.32
     frequently
    0.31
     continuously
    0.29
     throughout
    0.28
     Throughout
    0.26
     regularly
    0.26
     periodic
    0.26
    Activations Density 0.500%

    No Known Activations