© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44818
    Prev
    Next
    INDEX
    Explanations

    č issues

    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
    .Unmarshal
    -0.07
    æ±İ
    -0.06
    åı¯ä¸į
    -0.06
    ТС
    -0.06
    æµģè¨Ģ
    -0.06
    åĴ¨
    -0.06
    ÑĤал
    -0.06
    漫
    -0.06
    è°IJ
    -0.06
    åIJĥä¸į
    -0.06
    POSITIVE LOGITS
    ÙĴد
    0.08
    讯
    0.07
    iliz
    0.07
    å¸ĥå±Ģ
    0.07
    urie
    0.07
    aturi
    0.07
    lou
    0.07
    dojo
    0.07
    sess
    0.07
    eph
    0.07
    Activations Density 0.061%

    No Known Activations