© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8789
    Prev
    Next
    INDEX
    Explanations

    function/instruction/jQuery/citation suffixes

    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
    uably
    -0.08
    MITTED
    -0.08
    plement
    -0.07
    yce
    -0.07
    ––
    -0.07
    rieved
    -0.07
    schap
    -0.07
    éħĿ
    -0.06
    _collect
    -0.06
     copil
    -0.06
    POSITIVE LOGITS
    å°ıå±±
    0.07
    åľ¨è¯»
    0.06
     Ord
    0.06
    anas
    0.06
    'H
    0.06
    ä¸Ĭ楼
    0.06
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.06
    _ht
    0.06
    ]){
    0.06
    æłĩåĩĨä¿¡æģ¯
    0.06
    Activations Density 0.026%

    No Known Activations