© 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. 23011
    Prev
    Next
    INDEX
    Explanations

    de, git, Manchester, Harris, TERM, ants

    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
    æī¿
    -0.07
    åĨµ
    -0.06
    æİł
    -0.06
    éĿłè¿ij
    -0.06
    landa
    -0.06
    æľī家
    -0.06
    ä¸Ĭä¼łèĢħ
    -0.06
    æĺ¥èī²
    -0.06
     Daw
    -0.06
    IMG
    -0.06
    POSITIVE LOGITS
    odar
    0.09
    ä¹ĭçĪ¶
    0.08
    ãģ¨ãģĦãģĪãģ°
    0.08
    çļĦç»ıåħ¸
    0.08
    วà¸Ļ
    0.07
    ç»ıåħ¸çļĦ
    0.07
    æĪij们éĥ½çŁ¥éģĵ
    0.07
    æĹłçĸij
    0.07
     epic
    0.07
    ç»ıåħ¸
    0.07
    Activations Density 0.353%

    No Known Activations