© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42129
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    ùng
    -0.09
    enes
    -0.08
    ière
    -0.07
    éĢĤ
    -0.07
    泡
    -0.07
    jung
    -0.07
    eon
    -0.07
    ece
    -0.07
    uin
    -0.07
    Pointer
    -0.07
    POSITIVE LOGITS
    eteria
    0.07
    clin
    0.07
    abit
    0.07
    ç»Ļå®ļ
    0.07
    .gstatic
    0.06
    çŀ»
    0.06
    ulk
    0.06
    æĢ»éĩıçļĦ
    0.06
    unning
    0.06
    uns
    0.06
    Activations Density 0.065%

    No Known Activations