© 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. 21847
    Prev
    Next
    INDEX
    Explanations

    is / are / be

    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
     accompanying
    -0.08
    utar
    -0.08
    .SO
    -0.07
     оÑĤÑģÑĥÑĤ
    -0.07
    ä»
    -0.07
     ensuing
    -0.06
    ushman
    -0.06
    ãģĿ
    -0.06
    è¿Ļä¸ªæľºä¼ļ
    -0.06
    reon
    -0.06
    POSITIVE LOGITS
     داراÛĮ
    0.08
    amani
    0.08
    quanto
    0.07
    æĺ¯å®Įåħ¨
    0.07
    oris
    0.07
    æĪij说
    0.07
    ombang
    0.07
    gota
    0.07
     entirely
    0.07
    ={({
    0.07
    Activations Density 0.492%

    No Known Activations