© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    limit of x to 1

    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
    åľ¨çľģ
    -0.08
    ibaldi
    -0.08
    çľģä¸ĭ
    -0.08
    æĬĢæľ¯æĶ¹éĢł
    -0.08
    /status
    -0.08
    大åįİ
    -0.07
    è§Ĵèī²æī®æ¼Ķ
    -0.07
    etro
    -0.07
    Commit
    -0.07
    _commit
    -0.07
    POSITIVE LOGITS
    è¿Ļ天
    0.08
    onie
    0.07
    åĩºäºİ
    0.07
     Domen
    0.06
    ÙĨÙĬÙĨ
    0.06
    _backend
    0.06
    æĿ
    0.06
    æĸ¹åı¯
    0.06
    ä½Ĩæĺ¯å¯¹äºİ
    0.06
    irin
    0.06
    Activations Density 0.005%

    No Known Activations