© 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. 45127
    Prev
    Next
    INDEX
    Explanations

    function f(x)

    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
    bjerg
    -0.08
    heus
    -0.07
     наÑģи
    -0.06
    -0.06
    /static
    -0.06
    burgh
    -0.06
    linkplain
    -0.06
    erville
    -0.06
    ysis
    -0.06
    å¿ĥéĩĮçļĦ
    -0.06
    POSITIVE LOGITS
    functions
    0.07
    emn
    0.07
    kaz
    0.07
    ÑĦÑĥнкÑĨи
    0.07
     kaz
    0.07
    çݺ
    0.06
    à¸Ńà¸Ń
    0.06
    RAD
    0.06
    atti
    0.06
     cant
    0.06
    Activations Density 0.020%

    No Known Activations