© 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. 28216
    Prev
    Next
    INDEX
    Explanations

    Reuters

    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
    osi
    -0.07
    eryl
    -0.07
    èIJĮ
    -0.06
    欢è¿İæĤ¨çļĦ
    -0.06
     ÑĤоже
    -0.06
    å®ŀä¹łæľŁéĹ´
    -0.06
    åĻ¨çŃī
    -0.06
     Blocked
    -0.06
    ä¾Ŀæ³ķ追究责任
    -0.06
    iece
    -0.06
    POSITIVE LOGITS
    plorer
    0.08
    tility
    0.07
    apers
    0.07
    éħĴå±ĭ
    0.07
    ekaan
    0.07
     _______,
    0.07
    ?,?,?,?,
    0.07
    Õ¼
    0.07
    åİĨä»»
    0.07
    kah
    0.07
    Activations Density 0.003%

    No Known Activations