© 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. 15898
    Prev
    Next
    INDEX
    Explanations

    words indicating a state or condition

    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
    /from
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.07
    eldon
    -0.06
    并已
    -0.06
    å®ĥæīĢ
    -0.06
    æīĢ带æĿ¥çļĦ
    -0.06
    æīĢåĮħåIJ«
    -0.06
    itata
    -0.06
    -0.06
    /by
    -0.06
    POSITIVE LOGITS
    -wise
    0.11
    ÑĬÑĤ
    0.11
    ÙĮ
    0.10
    able
    0.10
    Ùĭ
    0.10
     wise
    0.09
    çļĦãģ«ãģ¯
    0.09
    åIJĮä¸Ĭ
    0.09
    ä¹ĭä¸Ģæĺ¯
    0.09
    åĨħ容åĮħæĭ¬
    0.09
    Activations Density 0.030%

    No Known Activations