© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    location and prepositions

    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
    æľīæĪIJæķĪ
    -0.08
    æĸ¯é¡¿
    -0.08
    handled
    -0.08
    å¿Į
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    urna
    -0.07
    اÙĥ
    -0.07
    ç²¾ç¥ŀä¸ĬçļĦ
    -0.07
    ãĥĵãĤ¢
    -0.07
    عÙĪ
    -0.06
    POSITIVE LOGITS
    éĿłè¿ij
    0.10
    ä½įäºİ
    0.10
     недалеко
    0.10
     located
    0.09
     near
    0.09
     tepatnya
    0.09
     situated
    0.08
    å¾Ĺ天çĭ¬
    0.08
     location
    0.08
    çļĦä½įç½®
    0.08
    Activations Density 0.767%

    No Known Activations