© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    namespace declarations

    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
    ayı
    -0.08
    åIJĥçĿĢ
    -0.07
    oule
    -0.07
    ×Ļת×Ķ
    -0.07
    水泡
    -0.07
    ª
    -0.07
    éĽĨåħ¨
    -0.07
    nowrap
    -0.07
    клÑİ
    -0.07
     Fanpage
    -0.07
    POSITIVE LOGITS
    оÑĢод
    0.06
    armor
    0.06
    λοί
    0.06
    ราย
    0.06
    aris
    0.06
    å²IJ
    0.06
    Bins
    0.06
     pÅĻip
    0.06
    uos
    0.06
    æĹħè¡Į
    0.06
    Activations Density 0.001%

    No Known Activations