© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    versatile, pluripotent, potent

    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
    ãģ£ãģ¨ãĤĬ
    -0.08
    ationen
    -0.08
    icale
    -0.08
    åIJĮå¿Ĺ们
    -0.07
    stelle
    -0.07
    åĴĮè§Ĩé¢ij
    -0.07
    ockey
    -0.07
     dens
    -0.07
    ation
    -0.07
    assen
    -0.07
    POSITIVE LOGITS
     capable
    0.09
    opus
    0.08
    æĹ¢èĥ½
    0.08
    äºİä¸Ģ身
    0.08
     versatile
    0.07
    ariant
    0.07
    两éĿ¢
    0.07
    INI
    0.07
    appable
    0.07
    atile
    0.07
    Activations Density 0.054%

    No Known Activations