© 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. 55287
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
     Mald
    -0.08
    人ä¸Ń
    -0.07
    æѧ
    -0.06
    _inode
    -0.06
     ÑĢезо
    -0.06
    åݻ认è¯ģ
    -0.06
    _threshold
    -0.06
    Ngh
    -0.06
    æ°Ľ
    -0.06
    èī¯
    -0.06
    POSITIVE LOGITS
    ç½²
    0.08
    ä¸įæİ¥åıĹ
    0.08
    lobber
    0.08
    æľ¬äººåľ¨
    0.08
    utton
    0.08
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
    æĿ¥æİ¥
    0.07
     relev
    0.07
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.07
    æĮĩå®ļ
    0.07
    Activations Density 0.090%

    No Known Activations