© 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. 19600
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    纳德
    -0.07
    æĢ§åŃIJ
    -0.06
    apan
    -0.06
    ä¸įçł´
    -0.06
    pn
    -0.06
    çĿ¡äºĨ
    -0.06
    æĬ±
    -0.06
    女åŃIJ
    -0.06
     fallout
    -0.06
    éłĺ
    -0.06
    POSITIVE LOGITS
    鸳
    0.09
    åݦ
    0.08
    _ALREADY
    0.08
    ,proto
    0.08
    viso
    0.07
    ETO
    0.07
    éºĴéºŁ
    0.07
    acin
    0.07
    leftright
    0.07
    ãģ¾ãģķ
    0.07
    Activations Density 0.021%

    No Known Activations