© 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. 12504
    Prev
    Next
    INDEX
    Explanations

    Journal abbreviations

    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
     waarin
    -0.10
    åĨħæľī
    -0.08
    ä¸Ńåĩºçİ°
    -0.08
    ä¸Ń大
    -0.08
    éĩĮéĿ¢çļĦ
    -0.08
    éĩĮéĿ¢
    -0.07
     emptied
    -0.07
    æ½
    -0.07
    Æ¡i
    -0.07
    è´Łåİĭ
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.10
     drauf
    0.08
    ä¸Ĭæĺ¯
    0.08
    ä¸Ĭæľī
    0.08
    ä¸Ĭè¦ģ
    0.07
     عÙĦÙĬÙĩا
    0.07
    onaut
    0.07
     waarop
    0.07
    ta
    0.07
    çİĭèı²
    0.07
    Activations Density 0.020%

    No Known Activations