© 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. 56593
    Prev
    Next
    INDEX
    Explanations

    traditional or regular patterns

    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
    áĥĿáĥij
    -0.08
    istr
    -0.08
    andest
    -0.07
    .getRuntime
    -0.07
    Ỽ
    -0.07
    /component
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    çī¹åĪ«æ³¨æĦı
    -0.07
    æĽ´æİ¥è¿ij
    -0.07
    incar
    -0.07
    POSITIVE LOGITS
     traditional
    0.08
     tradizionale
    0.08
    ä¼łç»ŁçļĦ
    0.08
    åİŁæľ¬çļĦ
    0.08
    ä¼łç»Ł
    0.08
    æŃ£å¸¸çļĦ
    0.08
    traditional
    0.07
     Traditional
    0.07
     conventional
    0.07
     normally
    0.07
    Activations Density 0.518%

    No Known Activations