© 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. 43671
    Prev
    Next
    INDEX
    Explanations

    Rust, Java, or math notation

    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
     laine
    -0.06
    æĶ¿åįıåī¯ä¸»å¸Ń
    -0.06
    arious
    -0.06
     {}).
    -0.06
    >>>>>>>
    -0.06
    wez
    -0.06
    hecy
    -0.06
    æĭį
    -0.06
    اة
    -0.06
    mpp
    -0.06
    POSITIVE LOGITS
    ritto
    0.07
    æĸ°ç§Ģ
    0.07
    oggler
    0.07
    åį³ä»¥
    0.07
    orb
    0.07
    æ¸ħæ²³
    0.07
    å¹²äºĭ
    0.06
    enn
    0.06
    eldo
    0.06
    åĩ¯è¿ª
    0.06
    Activations Density 0.003%

    No Known Activations