© 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. 41634
    Prev
    Next
    INDEX
    Explanations

    Arabic and other non-Latin scripts

    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
    ,
    -0.06
    è¿Ļæł·
    -0.06
     da
    -0.06
    cka
    -0.06
    /
    -0.06
    åĴĮ
    -0.06
    ing
    -0.06
    “
    -0.06
     India
    -0.06
    ‘
    -0.06
    POSITIVE LOGITS
    icont
    0.08
    éĿ¢çĽ¸
    0.08
    è¡Įä¹ĭ
    0.08
    à¸Ĭล
    0.08
    -webpack
    0.08
    ufe
    0.08
    едеÑĢа
    0.08
     Verona
    0.08
    çĿĢæĥ³
    0.07
    raz
    0.07
    Activations Density 0.001%

    No Known Activations