© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and variables

    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
    istring
    -0.08
    occhi
    -0.08
    iskan
    -0.08
    aneously
    -0.08
    itter
    -0.08
    ìķĪìĿĢ
    -0.07
    纨
    -0.07
    å¥Īä½ķ
    -0.07
    kken
    -0.07
    neider
    -0.07
    POSITIVE LOGITS
    енÑĮ
    0.07
    é«ĺ度çļĦ
    0.06
    ä¸Ķä¸į
    0.06
    ×ŀת
    0.06
    èĤ¡
    0.06
    base
    0.06
     fiz
    0.06
     base
    0.06
    èĴĻ
    0.06
    éģµ
    0.06
    Activations Density 0.022%

    No Known Activations