© 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. 29121
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    Ngu
    -0.08
    μμα
    -0.08
    AndGet
    -0.08
     Tew
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
    LAM
    -0.07
    åĴĮ建议
    -0.07
    /question
    -0.07
    moni
    -0.07
    伯æģ©
    -0.07
    POSITIVE LOGITS
    ice
    0.07
    /ge
    0.07
    .nasa
    0.07
    åIJĦä½į家éķ¿
    0.07
     Separ
    0.07
     olarak
    0.07
    ically
    0.07
    è
    0.06
    åŁİå¤ĸ
    0.06
    ge
    0.06
    Activations Density 0.183%

    No Known Activations