© 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. 18682
    Prev
    Next
    INDEX
    Explanations

    ISO standards and technical specifications

    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
    aron
    -0.07
    æĬĺ
    -0.07
    é¬
    -0.07
    .toCharArray
    -0.07
    ÙĪارÙĩ
    -0.06
    puis
    -0.06
    å±±æĻ¯åĮº
    -0.06
    Buf
    -0.06
     Berk
    -0.06
    ëĿ¼ìĦľ
    -0.06
    POSITIVE LOGITS
     Vigo
    0.08
     ArgumentNullException
    0.07
    大潮
    0.07
    isd
    0.07
    Ø¡
    0.07
    ä¸ĢæĿ¥
    0.07
    _ALLOC
    0.07
    设å®ļçļĦ
    0.06
    lite
    0.06
    ë°¸
    0.06
    Activations Density 0.032%

    No Known Activations