© 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. 58186
    Prev
    Next
    INDEX
    Explanations

    provide supply source

    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
    agno
    -0.08
    à°¿à°¤
    -0.08
    oyo
    -0.08
    ä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    -0.08
    ingo
    -0.08
    onna
    -0.07
    lichten
    -0.07
    ë
    -0.07
    elv
    -0.07
    ongyang
    -0.07
    POSITIVE LOGITS
     necessary
    0.08
     недоÑģÑĤа
    0.08
     supply
    0.08
    æºIJæºIJ
    0.07
     supplies
    0.07
    Supply
    0.07
    supply
    0.07
     Supply
    0.07
    æ°´åĴĮ
    0.07
     needed
    0.06
    Activations Density 0.017%

    No Known Activations