© 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. 61848
    Prev
    Next
    INDEX
    Explanations

    concepts and qualities

    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
    ä»ĭçŁ³
    -0.08
    æĮģãģ¤
    -0.07
    åħ»çļĦ
    -0.07
     dicon
    -0.07
    ľ
    -0.07
    Ñİз
    -0.06
    ANTES
    -0.06
    ä½Ĩæĺ¯å¥¹
    -0.06
    unky
    -0.06
    PU
    -0.06
    POSITIVE LOGITS
    ạm
    0.07
    çon
    0.07
     nonetheless
    0.06
    人åķĬ
    0.06
    oms
    0.06
    nown
    0.06
    _same
    0.06
     nämlich
    0.06
    ä¸Ĭèħº
    0.06
    æīĢåIJ¸å¼ķ
    0.06
    Activations Density 0.778%

    No Known Activations