© 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. 41593
    Prev
    Next
    INDEX
    Explanations

    fluorine, hydrides, and pentachloride

    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
    ä¸Ĭ好
    -0.08
    PILE
    -0.07
     Sloan
    -0.07
    iglio
    -0.07
    æݪæīĭ
    -0.07
     NYPD
    -0.07
    çĴIJ
    -0.07
    æĮģåį¡äºº
    -0.07
    åºķ线
    -0.07
    WithString
    -0.07
    POSITIVE LOGITS
    èĴ¸æ°Ķ
    0.08
    .exe
    0.07
     vap
    0.07
     atmosfer
    0.07
    åѵåĮĸåĻ¨
    0.07
    顺é£İ
    0.07
    aze
    0.07
    sex
    0.07
     gas
    0.06
    é»Ħé¾Ļ
    0.06
    Activations Density 0.006%

    No Known Activations