© 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. 9336
    Prev
    Next
    INDEX
    Explanations

    is something

    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
    è¿Ļæł·çļĦ
    -0.07
    æıIJ示信æģ¯
    -0.07
     incl
    -0.07
    ther
    -0.07
     cou
    -0.06
    ä¸įæĹ©
    -0.06
     hell
    -0.06
     ade
    -0.06
    ocode
    -0.06
    éĻĦ
    -0.06
    POSITIVE LOGITS
    à¸ķัà¸Ļ
    0.08
    'L
    0.08
    ienza
    0.07
     Sized
    0.07
    ÑģоÑĤ
    0.07
     ЧиÑĤайÑĤе
    0.07
     ÙĦاب
    0.07
    isial
    0.07
    веÑĢо
    0.07
    ä¹ĭåĨħ
    0.07
    Activations Density 0.004%

    No Known Activations