© 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. 57181
    Prev
    Next
    INDEX
    Explanations

    equations with variables to solve

    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
    ç³»çļĦ
    -0.07
    ç³»
    -0.07
    ics
    -0.07
    owie
    -0.07
    æĪİ
    -0.07
    wich
    -0.07
    ines
    -0.07
    oyer
    -0.07
    ç»Ħç»Ħéķ¿
    -0.06
    ik
    -0.06
    POSITIVE LOGITS
    êtement
    0.08
    åĸĿçĿĢ
    0.08
    æ¯ıä¸Ģ个人çļĦ
    0.07
    onar
    0.07
    asant
    0.07
    ahoma
    0.07
    ÙĪرÙĩ
    0.07
    alers
    0.07
    HttpStatus
    0.07
    ÑĤли
    0.07
    Activations Density 0.014%

    No Known Activations