© 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. 38511
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners

    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
    ฯ
    -0.07
    anson
    -0.06
    sson
    -0.06
    iaga
    -0.06
    æī«çłģåħ³æ³¨
    -0.06
    ä¸ĭæĮ«
    -0.06
    schema
    -0.06
    udou
    -0.06
    kamer
    -0.06
    æĹłè®ºæĺ¯
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.09
     chÄĥng
    0.08
    æĪijèĩªå·±
    0.08
    opic
    0.08
    ä»ĸèĩªå·±
    0.08
    itten
    0.08
    ä¸įå®ĮçļĦ
    0.08
     ÑģамиÑħ
    0.07
    ä¸įä½ıçļĦ
    0.07
    ãģıãģ«
    0.07
    Activations Density 0.447%

    No Known Activations