© 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. 38289
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    &e
    -0.07
    سط
    -0.06
    _embeddings
    -0.06
    oy
    -0.06
    èĮ«èĮ«
    -0.06
    æĬ¥
    -0.06
    åİĨæĿ¥
    -0.06
    ç»ĻåĪ«äºº
    -0.06
    IPP
    -0.06
     atoi
    -0.06
    POSITIVE LOGITS
    essler
    0.08
    YST
    0.07
    西åŁİ
    0.07
     irm
    0.07
    langs
    0.07
    hoven
    0.07
    appa
    0.07
    bef
    0.07
    循
    0.07
    æŶä¸ĭ
    0.07
    Activations Density 0.011%

    No Known Activations