© 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. 57862
    Prev
    Next
    INDEX
    Explanations

    additional reasons or mechanisms

    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
    åħ°è¾¾
    -0.07
    usz
    -0.07
    ekom
    -0.07
    ãģ¾ãģļãģ¯
    -0.07
     ëĮĢìĭł
    -0.07
    é¦ĸåħĪéľĢè¦ģ
    -0.06
    æĹ¢ä¸į
    -0.06
     ãģ¾ãģļãģ¯
    -0.06
    æijĩ
    -0.06
    æĺ¯æŶåĢĻ
    -0.06
    POSITIVE LOGITS
     nữa
    0.12
    ä¹ŁæľīåĪ©äºİ
    0.10
    æĸ¹éĿ¢ä¹Ł
    0.10
    ä¹Łæľīä¸Ģå®ļçļĦ
    0.10
    ä¹ŁåĽł
    0.09
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.09
     dodatkowo
    0.09
    è¿Ľä¸ĢæŃ¥ä¼ĺåĮĸ
    0.09
     further
    0.09
    ä¹Łä¸İ
    0.09
    Activations Density 0.021%

    No Known Activations