© 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. 23322
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
    大家éĥ½åľ¨
    -0.07
     اص
    -0.07
    eur
    -0.07
    éŨåħ³
    -0.07
     shut
    -0.06
    ANGE
    -0.06
     operacional
    -0.06
    é¥Ń
    -0.06
    大家éĥ½
    -0.06
     surtout
    -0.06
    POSITIVE LOGITS
     uta
    0.08
     дÑĥ
    0.07
    icode
    0.07
    åı¯åĸľ
    0.07
    abis
    0.07
    注æĦıçļĦæĺ¯
    0.06
    ÙĪبÙĬ
    0.06
    fortunately
    0.06
    åĽłèĢĮ
    0.06
     Hence
    0.06
    Activations Density 0.037%

    No Known Activations