© 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. 2637
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    /browse
    -0.09
    -online
    -0.08
    alat
    -0.08
    嵩
    -0.08
    åħ¨ç¾İ
    -0.07
    estes
    -0.07
    åįģåħ¨
    -0.07
    shint
    -0.07
    perf
    -0.07
    errick
    -0.07
    POSITIVE LOGITS
     Lo
    0.07
    åĪĩåħ¥
    0.07
    æ»´æ°´
    0.06
    اعت
    0.06
    æīĵåħ¥
    0.06
    表象
    0.06
    æĪIJ
    0.06
    ÑĤоÑĢ
    0.05
    ackets
    0.05
     canto
    0.05
    Activations Density 0.086%

    No Known Activations