© 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. 42302
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by a noun

    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
    çļĦæĺ¯
    -0.08
     Tý
    -0.08
    öld
    -0.07
    اÙĨÙĪ
    -0.07
    দà§ĩশ
    -0.06
    ologia
    -0.06
    plements
    -0.06
    arty
    -0.06
    azio
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
    à¯ģவ
    0.07
    å®īå¹³
    0.07
    ä¸½å¨ľ
    0.07
    -turned
    0.07
    æķĻäºİ
    0.07
    enä
    0.07
    finanz
    0.07
    -chief
    0.07
    tas
    0.07
    è´Łè´£åIJĮå¿Ĺ
    0.07
    Activations Density 0.094%

    No Known Activations