© 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. 49998
    Prev
    Next
    INDEX
    Explanations

    preposition followed by 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
    oday
    -0.07
    alia
    -0.06
    phe
    -0.06
    ila
    -0.06
    angel
    -0.06
    Rs
    -0.06
    os
    -0.06
    åłª
    -0.06
    è¿İçĿĢ
    -0.06
    åĽŀèĢģ家
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.08
    ç¥ŃãĤĬ
    0.08
    Å¡t
    0.08
    edly
    0.08
     lainnya
    0.08
     theirs
    0.07
    ::$_
    0.07
    åľ¨çľĭåĪ°
    0.07
    ÙĬرÙĭا
    0.07
    ä¸ĭä¸Ģç§Ĵ
    0.07
    Activations Density 0.302%

    No Known Activations