© 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. 47090
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases about location or relation

    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
    burgh
    -0.09
    åĪ©äºİ
    -0.08
    ssen
    -0.07
    ÙĪÙĥ
    -0.07
    ê·¼
    -0.07
    _APB
    -0.07
    åľĪ
    -0.07
    ksz
    -0.07
    .createNew
    -0.07
    代人
    -0.07
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.12
     thereof
    0.10
    åIJĮæł·çļĦ
    0.10
     SAME
    0.09
    åIJĮæł·
    0.09
     same
    0.09
     ebenfalls
    0.08
    缸åIJĮ
    0.08
    åı¦ä¸Ģ个
    0.08
    same
    0.08
    Activations Density 0.229%

    No Known Activations