© 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. 40733
    Prev
    Next
    INDEX
    Explanations

    `INSERT INTO` clauses

    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
    æľ½
    -0.07
    Locator
    -0.07
    élia
    -0.07
    rett
    -0.07
    trut
    -0.07
    .cgi
    -0.07
    åıijå±ķåĴĮæĶ¹éĿ©
    -0.07
    .loc
    -0.07
    anak
    -0.07
     اÙĦÙģÙĬ
    -0.07
    POSITIVE LOGITS
     Binh
    0.08
    สัà¸Ļ
    0.07
    schn
    0.07
    &a
    0.07
    IGN
    0.06
     arra
    0.06
    ewe
    0.06
    inline
    0.06
    åįļ士åѦä½į
    0.06
    zah
    0.06
    Activations Density 0.001%

    No Known Activations