© 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. 1996
    Prev
    Next
    INDEX
    Explanations

    analytic continuations, positive Gaussian, hyperbolic

    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
    ä¹Ŀé¾Ļ
    -0.07
    建åįİ
    -0.06
    æĩĤäºĭ
    -0.06
    æķĻ
    -0.06
    ç§ijæĸ¯
    -0.06
     manu
    -0.06
    èģª
    -0.06
    omics
    -0.06
    çİĭéģĵ
    -0.06
    éĻįåĪ°æľĢä½İ
    -0.06
    POSITIVE LOGITS
     analogue
    0.08
    emode
    0.08
    negative
    0.08
     analog
    0.08
    _transition
    0.08
    转åĮĸæĪIJ
    0.08
    è½īæıĽ
    0.07
    ãĥ³ãĤ¸
    0.07
    è´ŁçļĦ
    0.07
     Ansi
    0.07
    Activations Density 0.007%

    No Known Activations