© 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. 21153
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    estra
    -0.07
    æŀ·
    -0.07
    onia
    -0.07
    æŀª
    -0.07
    astre
    -0.07
    odr
    -0.06
     arbitrary
    -0.06
    æľ½
    -0.06
    ekat
    -0.06
    æ¤
    -0.06
    POSITIVE LOGITS
    abouts
    0.09
    ç§ijæĬĢåѦéĻ¢
    0.08
    (mac
    0.08
    /docker
    0.08
    è¦ģæĿ¥
    0.08
    ÅĦczy
    0.07
    avern
    0.07
    issan
    0.07
    uthor
    0.07
    auss
    0.06
    Activations Density 0.000%

    No Known Activations