© 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. 30681
    Prev
    Next
    INDEX
    Explanations

    copyright notice, disclaimer, common ratio, found in, video chats, package scilab

    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
    äºİè¡Į
    -0.07
    é¢Ĩåıĸ
    -0.07
    é¢Ĩ
    -0.07
    oso
    -0.07
    rets
    -0.06
    çĴĭ
    -0.06
    oy
    -0.06
     VA
    -0.06
    æ¿Ģ
    -0.06
    éģĹåĺ±
    -0.06
    POSITIVE LOGITS
    åĿIJä¸ĭæĿ¥
    0.08
    upal
    0.07
    unk
    0.07
    èĪĴæľįçļĦ
    0.07
    åı¸ç©º
    0.07
    atched
    0.07
    mun
    0.07
     zeg
    0.07
    antara
    0.07
    mf
    0.07
    Activations Density 0.111%

    No Known Activations