© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62562
    Prev
    Next
    INDEX
    Explanations

    prime factors, divisibility, or mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esten
    -0.08
    Įĵ
    -0.07
    ê¸ī
    -0.07
    anton
    -0.07
    akai
    -0.06
    ×Ļת×Ļ
    -0.06
    ála
    -0.06
     revit
    -0.06
    гка
    -0.06
    cati
    -0.06
    POSITIVE LOGITS
     usually
    0.07
     ines
    0.07
     STDERR
    0.07
    entions
    0.07
    .present
    0.06
    PRINTF
    0.06
    æĸĮ
    0.06
    pection
    0.06
    zan
    0.06
    alow
    0.06
    Activations Density 0.038%

    No Known Activations