© 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. 63967
    Prev
    Next
    INDEX
    Explanations

    static keyword in code

    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
    ato
    -0.07
    azon
    -0.07
    ÙĬص
    -0.07
    atio
    -0.07
    anto
    -0.06
    ÙĬرÙĪ
    -0.06
    iro
    -0.06
    lle
    -0.06
    iat
    -0.06
    esa
    -0.06
    POSITIVE LOGITS
     óp
    0.08
    à¸ģัà¸Ļà¹ĥà¸Ļ
    0.08
    aupts
    0.08
    yped
    0.07
    ká
    0.07
    çIJª
    0.07
    rachten
    0.07
    ì§ģ
    0.07
    urus
    0.07
    OnError
    0.07
    Activations Density 0.068%

    No Known Activations