© 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. 57418
    Prev
    Next
    INDEX
    Explanations

    top physics

    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
    åįİåºľ
    -0.08
    æĭĿ
    -0.08
    egot
    -0.07
    æł©
    -0.07
    åĴĮå®ŀæĸ½
    -0.07
    åľ¨åŃ¦æł¡
    -0.07
    æļĩ
    -0.07
    款
    -0.07
     substanc
    -0.06
    Ĵáŀ
    -0.06
    POSITIVE LOGITS
    åĴĮé»ij
    0.07
    oba
    0.07
    etid
    0.07
    мали
    0.07
    åĵ¨
    0.07
    ÙĨاء
    0.07
    çŃī大åŀĭ
    0.07
     máu
    0.07
    quake
    0.07
    ess
    0.07
    Activations Density 0.010%

    No Known Activations