© 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. 40626
    Prev
    Next
    INDEX
    Explanations

    application of

    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
    oque
    -0.09
    tingham
    -0.08
    ilers
    -0.08
    åıĪä¼ļ
    -0.08
    ç»Ħç»ĩäºĨ
    -0.08
    меннаÑı
    -0.07
    æİĴåIJį第
    -0.07
    ãģĵãĤĮãĤĴ
    -0.07
    ÑĤил
    -0.07
    รี
    -0.07
    POSITIVE LOGITS
    个人æĪĸ
    0.10
    éĢļè¿ĩåIJĦç§į
    0.09
    æŁIJä¸Ģ
    0.09
    æŁIJ
    0.09
    çļĦä¸Ģç§į
    0.08
     suatu
    0.08
    æŁIJ个
    0.08
    çļĦä¸Ģç»Ħ
    0.08
    åľ¨æŁIJ
    0.08
    æŁIJç§į
    0.08
    Activations Density 0.427%

    No Known Activations