© 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. 30400
    Prev
    Next
    INDEX
    Explanations

    http urls, JSON, lists, names

    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
    æĢ§ä»·æ¯Ķ
    -0.07
     Richardson
    -0.06
    æĢ§ä»·æ¯Ķé«ĺ
    -0.06
    _EXIST
    -0.06
    åĨĽçļĦ
    -0.06
     B
    -0.06
     ist
    -0.06
    æ¯Ķè¾ĥéĢĤåIJĪ
    -0.06
    åĪĩåı£
    -0.06
     \/
    -0.06
    POSITIVE LOGITS
    æľ¬é¢ĺåĪĨæŀIJ
    0.09
    LinkId
    0.08
    uoja
    0.07
    PageRoute
    0.07
    árov
    0.07
    landers
    0.07
    UnderTest
    0.07
    [start
    0.07
    éĻµåİ¿
    0.07
    åĬłæĭ¿å¤§
    0.07
    Activations Density 0.011%

    No Known Activations