© 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. 39852
    Prev
    Next
    INDEX
    Explanations

    Observable, Observer, ResponseEntity, List, T, App, Contact

    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
    ित
    -0.07
    æ·±æĢĿ
    -0.07
     Hung
    -0.06
    å¿
    -0.06
    æĩ¸
    -0.06
    ä¹ĥæĺ¯
    -0.06
    åĭĴæĸ¯
    -0.06
    RIGHT
    -0.06
    æĺ¯ä¸ĢåIJį
    -0.06
    é»į
    -0.06
    POSITIVE LOGITS
    alang
    0.10
    vell
    0.08
    éĹĨ
    0.07
     Nur
    0.07
    aho
    0.07
    ä¸įå¾Ĺ以任ä½ķ
    0.07
    quio
    0.07
    lica
    0.07
    äºİä¸ĸ
    0.07
    Wrapped
    0.07
    Activations Density 0.235%

    No Known Activations