© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    input / from

    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
    astos
    -0.07
    人æ°ijåħ±åĴĮåĽ½
    -0.06
    /GPL
    -0.06
    ekar
    -0.06
     Math
    -0.06
    人æīĢ
    -0.06
    _Tag
    -0.06
    *e
    -0.06
    对æĸ¹å½ĵäºĭ人
    -0.06
     merits
    -0.06
    POSITIVE LOGITS
    ä¸ĩäºĭå¦ĤæĦı
    0.07
    èݱåĿŀ
    0.07
    etz
    0.07
    Å«t
    0.07
    hes
    0.07
    idin
    0.07
    ç»ĻçļĦ
    0.06
    .detect
    0.06
    apt
    0.06
    оÑĢÑı
    0.06
    Activations Density 0.007%

    No Known Activations