© 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. 39595
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    dá
    -0.08
    èļĢ
    -0.07
     Disqus
    -0.07
    zub
    -0.07
    æĸĩ广
    -0.07
    baugh
    -0.06
    __.__
    -0.06
     Skinny
    -0.06
    éĵIJ
    -0.06
    mán
    -0.06
    POSITIVE LOGITS
    ä¸Ĭæŀ¶
    0.08
    ç¹ģ
    0.07
    åĨ³ä¸į
    0.07
    æīĢåij¨
    0.07
    çº¢é¢ľ
    0.07
    formats
    0.07
    olist
    0.07
    unn
    0.07
    羨
    0.06
    ja
    0.06
    Activations Density 0.008%

    No Known Activations