© 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. 57297
    Prev
    Next
    INDEX
    Explanations

    greeting everyone

    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
    ä»ĸå¸ĮæľĽ
    -0.09
    ä»ĸè§īå¾Ĺ
    -0.08
    让对æĸ¹
    -0.08
    GetInstance
    -0.08
    çīĪæĿĥåĿĩ
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
    GetWidth
    -0.08
    _KEYWORD
    -0.08
    ungan
    -0.08
    POSITIVE LOGITS
    ç»Ļ大家æݨèįIJ
    0.07
     recently
    0.07
    æľĢè¿ij
    0.07
     here
    0.07
    çİ°å°±
    0.07
    ç»Ļ大家ä»ĭç»į
    0.07
     наконеÑĨ
    0.06
    å¾Īé«ĺåħ´
    0.06
    âĢIJ
    0.06
     Recently
    0.06
    Activations Density 2.243%

    No Known Activations