© 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. 27318
    Prev
    Next
    INDEX
    Explanations

    recent publications and studies

    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
    ieli
    -0.07
     baseUrl
    -0.07
    HWND
    -0.07
    æīİ
    -0.07
    ä½Ĩä»ĸ
    -0.06
    好åIJ§
    -0.06
     Merci
    -0.06
     ‘’
    -0.06
     profoundly
    -0.06
     изÑĬÑı
    -0.06
    POSITIVE LOGITS
     document
    0.09
    ccording
    0.08
     documented
    0.08
     reported
    0.08
    document
    0.07
    Document
    0.07
    åĤ¬
    0.07
    æĸĩæ¡£
    0.07
    æł¹æį®
    0.07
    æĬ¥åijĬä¸Ń
    0.07
    Activations Density 0.006%

    No Known Activations