© 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. 58108
    Prev
    Next
    INDEX
    Explanations

    more likely than

    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
    åıĪä»İ
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    ibun
    -0.07
    ä¹Łç¡®å®ŀ
    -0.07
    ç»Ŀä¸įæĺ¯
    -0.07
    åIJĮæŶåıĪ
    -0.07
    ä¹Łä¸įåĨį
    -0.07
    į°
    -0.07
    olg
    -0.07
    çĻ½çŁ³
    -0.07
    POSITIVE LOGITS
    è¿ĺä¸įå¦Ĥ
    0.11
    çĶļèĩ³æ¯Ķ
    0.10
     بÙĥØ«ÙĬر
    0.09
    缸æ¯Ķä¹ĭä¸ĭ
    0.08
    ãģ®ãģ»ãģĨãģĮ
    0.08
    ãģ»ãģĨãģĮ
    0.08
    åı¯æ¯Ķ
    0.08
    åIJĮçŃī
    0.08
    ä¸įå¦Ĥ
    0.08
    than
    0.07
    Activations Density 0.213%

    No Known Activations