© 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. 15887
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and functions

    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
    ä¼ijçľł
    -0.07
    _OPT
    -0.07
    éħĹ
    -0.07
    æīĭæľºéĺħ读
    -0.07
    íĦ°ë¦¬
    -0.07
    æĸĩåĮĸ课
    -0.07
    .backends
    -0.07
    cita
    -0.07
    ovich
    -0.07
    绪
    -0.07
    POSITIVE LOGITS
     partial
    0.08
    å±ħé«ĺ
    0.08
     Identity
    0.07
    身åĪĨ
    0.07
    ossa
    0.07
    .partial
    0.07
     subtract
    0.07
     Partial
    0.07
    oss
    0.07
    Exchange
    0.07
    Activations Density 0.003%

    No Known Activations