© 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. 56891
    Prev
    Next
    INDEX
    Explanations

    $key updates or assignments

    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
    é¡·åĪ»
    -0.07
    æ¼¾
    -0.07
    é±¼åĦ¿
    -0.06
    IAS
    -0.06
    оÑĤи
    -0.06
    üh
    -0.06
    åIJĦè¡Į
    -0.06
    éĵģè·¯è¿IJè¾ĵ
    -0.06
     entst
    -0.06
    ä¿ĿæķĻ
    -0.06
    POSITIVE LOGITS
    æŁIJ
    0.12
    åľ¨æŁIJ
    0.12
    æŁIJ个
    0.11
    æŁIJä¸Ģ
    0.10
    æŁIJ人
    0.10
    æŁIJåĢĭ
    0.10
     XYZ
    0.10
    æŁIJç§į
    0.10
     magari
    0.09
    æŁIJä¸Ģ天
    0.09
    Activations Density 0.348%

    No Known Activations