© 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. 42470
    Prev
    Next
    INDEX
    Explanations

    directly followed by 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
     truly
    -0.08
    ä¹ĭèĬ±
    -0.07
    art
    -0.07
    è¿Ļç§įçĸ¾çĹħ
    -0.07
     právÄĽ
    -0.07
    erber
    -0.07
     ë°ĺëĵľìĭľ
    -0.07
    æĢ»åħ±
    -0.07
    æķ´æķ´
    -0.07
     seulement
    -0.07
    POSITIVE LOGITS
    ë°Ķë¡ľ
    0.09
    à¹Ģลยวà¹Īา
    0.09
    à¹Ģลย
    0.09
    eous
    0.08
    æĪIJç«ł
    0.08
    azan
    0.07
    à¹Ģลยà¸Ħรัà¸ļ
    0.07
    ä¸Ĭæīĭ
    0.07
    à¹Ģลยà¸Ħà¹Īะ
    0.07
    incu
    0.07
    Activations Density 0.023%

    No Known Activations