© 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. 18439
    Prev
    Next
    INDEX
    Explanations

    balance and totals

    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
     kors
    -0.08
    olé
    -0.07
    _sampling
    -0.07
    otar
    -0.07
    Į¨
    -0.07
    ç«ŀäºīæ¿ĢçĥĪ
    -0.07
     matur
    -0.07
    ÑĢабоÑĤки
    -0.07
    çĻ¾èĬ±
    -0.07
    agraph
    -0.07
    POSITIVE LOGITS
    平衡
    0.08
     balance
    0.08
    æł¸å¯¹
    0.08
     balanced
    0.08
     totals
    0.07
     match
    0.07
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½
    0.07
     баланÑģа
    0.07
    ä¸į平衡
    0.07
    alance
    0.07
    Activations Density 0.001%

    No Known Activations