© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    while loops and variable declarations

    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
    âĢİ
    -0.07
    ©
    -0.07
    ละ
    -0.07
    sequ
    -0.07
    adel
    -0.07
     Hels
    -0.06
    igten
    -0.06
    squ
    -0.06
    ethe
    -0.06
    åºı
    -0.06
    POSITIVE LOGITS
    arkin
    0.09
    å©¿
    0.08
    åĪ©æĸ¯
    0.07
    çļĦä¸Ń
    0.07
     midpoint
    0.07
    rawer
    0.07
     полови
    0.07
     Inherits
    0.07
    coles
    0.07
    æĻ
    0.07
    Activations Density 0.001%

    No Known Activations