© 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. 15869
    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
    以ä¸ĬçļĦ
    -0.08
    dent
    -0.06
    ffin
    -0.06
    çļĦå¤ĦçIJĨ
    -0.06
    ³³³³³³³
    -0.06
    æ°¸åħ´
    -0.06
    天éķ¿
    -0.06
    èIJ½åIJİçļĦ
    -0.06
     Face
    -0.06
    Ùĩج
    -0.06
    POSITIVE LOGITS
    ç£Ĭ
    0.08
    QUIS
    0.07
    ameron
    0.07
    ç«£
    0.07
    дии
    0.07
    _CY
    0.07
     miscellaneous
    0.07
    akil
    0.07
    Curso
    0.07
    olumn
    0.07
    Activations Density 0.097%

    No Known Activations