© 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. 63927
    Prev
    Next
    INDEX
    Explanations

    quadratic function 2

    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
    é¦ı
    -0.09
    åĪºæ¿ĢçļĦ
    -0.08
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.08
    streams
    -0.08
    биÑĢа
    -0.07
    åĪºæ¿Ģ
    -0.07
    ARED
    -0.07
    ç´³
    -0.07
    大éĢļ
    -0.07
    éĿłåīį
    -0.07
    POSITIVE LOGITS
     parab
    0.09
     quadratic
    0.08
     Parab
    0.08
    æĬĽçī©
    0.08
    å¼Ģåı£
    0.08
    äºĮ次
    0.07
     upward
    0.07
     upside
    0.07
    adratic
    0.07
    éĶħåºķ
    0.07
    Activations Density 0.003%

    No Known Activations