© 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. 28121
    Prev
    Next
    INDEX
    Explanations

    foundation for or of

    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
    天边
    -0.11
    髦
    -0.08
    enaar
    -0.08
    andering
    -0.07
    aptcha
    -0.07
    atoire
    -0.07
    ستاÙĨ
    -0.07
    ä¿±è¿Ľ
    -0.07
    мога
    -0.07
    зне
    -0.07
    POSITIVE LOGITS
     vững
    0.12
     tảng
    0.12
    åĿļå®ŀ
    0.12
     foundation
    0.11
    ä¸į稳
    0.11
     foundations
    0.11
    æł¹åŁº
    0.10
    ç¨³åĽº
    0.10
     اÙĦتØŃتÙĬØ©
    0.10
    åĿļå®ŀçļĦ
    0.10
    Activations Density 0.065%

    No Known Activations