© 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. 16043
    Prev
    Next
    INDEX
    Explanations

    linking verbs followed by nouns or adjectives

    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
    chado
    -0.08
    æķĻèĤ²æĺ¯
    -0.08
    鼷æĸ¯
    -0.08
    åĿŀ
    -0.07
    ugin
    -0.07
    æĥħåĨµè¿Ľè¡ĮäºĨ
    -0.07
    ellig
    -0.07
    AMAN
    -0.07
    ä»Ģä¹Īæł·çļĦ
    -0.07
    enko
    -0.07
    POSITIVE LOGITS
     berupa
    0.10
    apt
    0.08
    entu
    0.08
    entar
    0.07
     próprio
    0.07
    ä¸įéĻIJäºİ
    0.07
    ãģŁãĤĭ
    0.07
     ëĶ°ë¡ľ
    0.07
    涯
    0.06
    ì²´ìĿ¸
    0.06
    Activations Density 0.094%

    No Known Activations