© 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. 20418
    Prev
    Next
    INDEX
    Explanations

    triangle inequality theorem

    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
     Patron
    -0.09
    ļĮ
    -0.09
     patron
    -0.08
    交éģĵ
    -0.08
    folio
    -0.08
    IDGET
    -0.08
    ernaut
    -0.07
    æĭĿ
    -0.07
    çķij
    -0.07
    åĭ¤
    -0.07
    POSITIVE LOGITS
     triangle
    0.08
    triangle
    0.07
    æĪIJç«ĭçļĦ
    0.07
     Triangle
    0.07
     ìĤ¼
    0.07
    acute
    0.06
    åı¯è¡Į
    0.06
    L
    0.06
    ä¸īè§Ĵå½¢çļĦ
    0.06
    éĥ¨èIJ½
    0.06
    Activations Density 0.002%

    No Known Activations