© 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. 46515
    Prev
    Next
    INDEX
    Explanations

    so much

    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
    ĩ
    -0.07
    icolor
    -0.06
    aims
    -0.06
    -0.06
    esan
    -0.06
    aleza
    -0.06
    indo
    -0.06
    <?
    -0.06
    orr
    -0.06
    opensource
    -0.06
    POSITIVE LOGITS
    imei
    0.08
    ula
    0.07
    mts
    0.07
    泡èıľ
    0.07
    ×ŀצ
    0.07
    кеÑĢа
    0.07
     Stav
    0.07
    æĸĩåѦéĻ¢
    0.07
    åIJ¯ç¤º
    0.07
    லà¯Ī
    0.07
    Activations Density 0.131%

    No Known Activations