© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    mathematical probability statements

    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
    añ
    -0.08
    _hooks
    -0.08
    主åŃIJ
    -0.08
    度åĴĮ
    -0.08
    度è¿ĩ
    -0.08
    æİĸ
    -0.07
    äºĮ度
    -0.07
    ç»Ĭ
    -0.07
    Hooks
    -0.07
    oons
    -0.07
    POSITIVE LOGITS
    模åŀĭçļĦ
    0.08
    è¿Ļæī¹
    0.07
    åijĽ
    0.07
    éľĨ
    0.07
     fore
    0.07
    èĢ½
    0.07
    PERT
    0.07
    cert
    0.06
     cert
    0.06
     اÙĦرش
    0.06
    Activations Density 0.009%

    No Known Activations