© 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. 60460
    Prev
    Next
    INDEX
    Explanations

    math expressions and calculations

    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
     conta
    -0.07
    ä¹ĭé¦ĸ
    -0.06
    é¦ĸ
    -0.06
    illas
    -0.06
    odable
    -0.06
    æľ½
    -0.06
    aja
    -0.06
    ieg
    -0.06
    cla
    -0.06
    ensored
    -0.06
    POSITIVE LOGITS
    _PS
    0.08
    ç»ĻåĬĽ
    0.07
    Ĺı
    0.07
    èĥ½åĬĽæıIJåįĩ
    0.07
    è¡¥é½IJ
    0.07
    æ±IJ
    0.07
    çĥ¨
    0.07
    нÑıка
    0.07
    Fatal
    0.07
    á»įt
    0.07
    Activations Density 0.003%

    No Known Activations