© 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. 12202
    Prev
    Next
    INDEX
    Explanations

    providing services or solutions

    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
     sufficiently
    -0.06
    _busy
    -0.06
    æĸĩ件æĪĸ
    -0.06
    .contents
    -0.06
    ekar
    -0.06
    çļĦéĩįè¦ģåĽłç´ł
    -0.06
    以ä¸ĭæŃ¥éª¤
    -0.06
    ä¹ĭåĬ¿
    -0.06
    ä¸įå¾Ĺä¸į
    -0.06
    èĤ¥
    -0.06
    POSITIVE LOGITS
     primarily
    0.11
     ì£¼ë¡ľ
    0.11
    主ãģ«
    0.10
     principally
    0.10
     mainly
    0.10
     principalement
    0.10
     principalmente
    0.09
     chiefly
    0.09
    起家
    0.09
     widest
    0.08
    Activations Density 1.287%

    No Known Activations