© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    mothers and parents

    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
    å°ıä¼Ļ伴们
    -0.08
    æĮĸæİĺåħ¬åı¸
    -0.08
    å¸Ī妹
    -0.08
    orte
    -0.08
    å¸Īå§IJ
    -0.08
    åIJĦç§ij室
    -0.07
    _authentication
    -0.07
    çķĻæģĭ
    -0.07
    为人们
    -0.07
    让åIJĮåѦ们
    -0.07
    POSITIVE LOGITS
    èĤ²åĦ¿
    0.15
    åľ¨åŃ©åŃIJ
    0.14
    对åŃ©åŃIJ
    0.14
     parenting
    0.14
    对åŃ©åŃIJçļĦ
    0.14
    åĴĮåŃ©åŃIJ
    0.13
    ä¸İåŃ©åŃIJ
    0.12
    åħ»èĤ²
    0.12
    æĬĬåŃ©åŃIJ
    0.12
    åŃ©åŃIJçļĦ
    0.11
    Activations Density 0.364%

    No Known Activations