© 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. 28136
    Prev
    Next
    INDEX
    Explanations

    programming comments and keywords

    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
    áĥĵáĥĶ
    -0.08
     gesta
    -0.08
    feuer
    -0.08
    êm
    -0.08
    afen
    -0.07
    lable
    -0.07
    çļĦä¸ĢäºĽ
    -0.07
    ianos
    -0.07
    वल
    -0.07
    xem
    -0.07
    POSITIVE LOGITS
    ikal
    0.07
    建ç«ĭèī¯å¥½çļĦ
    0.07
    cl
    0.07
    ation
    0.06
    åŁºæľ¬è¦ģæ±Ĥ
    0.06
    ä½ľå¥½
    0.06
    æĿ¥ä¸ª
    0.06
     foundational
    0.06
     comparison
    0.06
    ä¿ĿæĮģèī¯å¥½çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations