© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46690
    Prev
    Next
    INDEX
    Explanations

    statistical variables and regression

    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
    /octet
    -0.07
     Bom
    -0.07
     transparent
    -0.07
     Ern
    -0.07
    æĻĭ级
    -0.07
     numeral
    -0.07
    ç¾Ķ
    -0.06
    ķĮ
    -0.06
    é»į
    -0.06
    rog
    -0.06
    POSITIVE LOGITS
    çº
    0.09
     regress
    0.07
    ç»Łè®¡åĪĨæŀIJ
    0.07
    anca
    0.07
    STAT
    0.07
    Ùħز
    0.07
    urm
    0.07
    ç»Łè®¡
    0.07
    æķ°æį®ç»Łè®¡
    0.07
    Stat
    0.07
    Activations Density 0.003%

    No Known Activations