© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14630
    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
     ÑģколÑĮ
    -0.07
    www
    -0.06
    è¿ĩç¥ŀ
    -0.06
    agi
    -0.06
    bench
    -0.06
    èĢĮçŁ¥
    -0.06
    æĭ©ä¼ĺ
    -0.06
    autoload
    -0.06
    łĢ
    -0.06
     collectively
    -0.06
    POSITIVE LOGITS
    åľ¨è§Ħå®ļ
    0.08
    pliers
    0.08
    unds
    0.08
    ساد
    0.08
    ripp
    0.08
     cias
    0.08
    èĥ½åĬĽåĪĨæŀIJ
    0.08
    idere
    0.08
    oris
    0.08
    åIJįå½ķ
    0.08
    Activations Density 0.000%

    No Known Activations