© 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. 39087
    Prev
    Next
    INDEX
    Explanations

    infinite scroll, API operations, easing function, Clifford algebra, training program

    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
    ỡ
    -0.07
    routeParams
    -0.07
    ìķĻ
    -0.07
    SSION
    -0.07
    ä¾ĽåºĶ产åĵģ
    -0.07
    erus
    -0.07
    Ñģий
    -0.07
    æ§Ľ
    -0.07
    оÑĤÑı
    -0.07
    ftime
    -0.07
    POSITIVE LOGITS
    umba
    0.07
    ISA
    0.06
     Benn
    0.06
    tabs
    0.06
    æĪĸèĢħ缴æİ¥
    0.06
    -like
    0.06
    unno
    0.06
     Ga
    0.06
    ä¸įèĥľ
    0.06
     Altre
    0.06
    Activations Density 0.100%

    No Known Activations