© 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. 51242
    Prev
    Next
    INDEX
    Explanations

    measurement of

    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
    moni
    -0.07
    аÑĨи
    -0.07
    ugat
    -0.07
    KHR
    -0.07
    bson
    -0.07
    ิà¸ļ
    -0.07
    ovar
    -0.07
    _initializer
    -0.07
    airo
    -0.06
    ÑĤоÑĢи
    -0.06
    POSITIVE LOGITS
    ãĤĵãģ³
    0.09
    漫漫
    0.08
    代ä¹ĭ
    0.07
    alkan
    0.07
    ood
    0.07
     immediata
    0.07
    ä¸īè¿ŀ
    0.07
    inander
    0.07
     inmediata
    0.07
    æ°¸åĪ©
    0.06
    Activations Density 0.902%

    No Known Activations