© 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. 31766
    Prev
    Next
    INDEX
    Explanations

    trouble-free, music, statement, enigmatic, convenience, problem

    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
     übrigens
    -0.09
    нав
    -0.08
     cÆ°Æ¡ng
    -0.08
    дев
    -0.08
    onnier
    -0.08
    ikian
    -0.07
    ÃīG
    -0.07
    azen
    -0.07
    ég
    -0.07
    idan
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.09
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    檸
    0.08
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    0.07
    ç®Ģ书
    0.06
    addir
    0.06
    çIJ¥
    0.06
    lbrace
    0.06
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½åIJĪåIJĮæ³ķ
    0.06
    ãģ«åıĸãĤĬ
    0.06
    Activations Density 0.001%

    No Known Activations