© 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. 60520
    Prev
    Next
    INDEX
    Explanations

    marker, stroke, opacity, colors

    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
    éªĩ
    -0.08
    éŃĶæĸ¹
    -0.07
     Gutsche
    -0.07
    æijĬ
    -0.07
    çĩķçªĿ
    -0.07
    çĭ¬ç§Ģ
    -0.07
    à¸įา
    -0.07
    _modules
    -0.07
    ียà¹Į
    -0.07
    BaseUrl
    -0.06
    POSITIVE LOGITS
    æł·å¼ı
    0.09
    é¢ľèī²
    0.09
    Opacity
    0.09
     marker
    0.09
     linestyle
    0.08
    /colors
    0.08
     markers
    0.08
    æłĩè®°
    0.08
     opacity
    0.08
    LineStyle
    0.08
    Activations Density 0.086%

    No Known Activations