© 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. 39275
    Prev
    Next
    INDEX
    Explanations

    lumen, surface, wall

    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
    heit
    -0.09
    ç³»ç»Łä¸ŃçļĦ
    -0.08
    arching
    -0.07
    /=
    -0.06
    nitz
    -0.06
    ãģªãģĹ
    -0.06
    .gov
    -0.06
    ald
    -0.06
    ä½ĵç³»ä¸Ń
    -0.06
    /mat
    -0.06
    POSITIVE LOGITS
     thereof
    0.11
     của
    0.09
    hoot
    0.08
     ενÏĮÏĤ
    0.08
    verb
    0.08
    দà§ĩশ
    0.08
    æī«ä¸Ģæī«
    0.08
     Của
    0.08
    OfClass
    0.08
    à¸Ĥà¸Ńà¸ĩ
    0.08
    Activations Density 0.162%

    No Known Activations