© 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. 26910
    Prev
    Next
    INDEX
    Explanations

    settling in, working perfectly

    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
     appunto
    -0.13
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.10
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    缴æİ¥æĪĸ
    -0.08
    åı¯æĥ³
    -0.08
     ÑģооÑĤвеÑĤÑģÑĤвенно
    -0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.08
    æľĢæĸ°æĸĩç«ł
    -0.08
     wÅĤaÅĽnie
    -0.08
    åĨįåĪ°
    -0.07
    POSITIVE LOGITS
     übrigens
    0.08
    ãĤĪãģĨãģ§
    0.07
    ãģĵãģ¨ãĤĦ
    0.07
    umba
    0.06
    æĪĸ
    0.06
    /
    0.06
    好èĩªå·±çļĦ
    0.06
    æĪĸèĢħæľī
    0.06
     bowiem
    0.06
    ãģ«ãģªãĤĬãģ¾ãģĻãģĮ
    0.06
    Activations Density 0.075%

    No Known Activations