© 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. 31299
    Prev
    Next
    INDEX
    Explanations

    academic citation years with numbers

    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
    笨
    -0.08
    ossi
    -0.08
    olini
    -0.08
    ä¸Ģåľ°
    -0.08
    usat
    -0.07
    -datepicker
    -0.07
    åħ¬åı¸ç»ıèIJ¥
    -0.07
    èĺĭ
    -0.07
    ÑĨÑı
    -0.07
    OUNT
    -0.07
    POSITIVE LOGITS
    nder
    0.06
    νια
    0.06
    amo
    0.06
    iates
    0.06
    voke
    0.06
    ien
    0.06
    æĿĸ
    0.06
    klar
    0.06
    åħ¥åºĵ
    0.06
    ราย
    0.06
    Activations Density 0.046%

    No Known Activations