© 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. 56998
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts

    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
    ç¾½
    -0.08
    ç¾½ç»Ĵ
    -0.07
    endah
    -0.07
    utig
    -0.07
    æĿĢæ°Ķ
    -0.07
     tov
    -0.07
    اÙĪ
    -0.07
    bacher
    -0.06
    éķIJ
    -0.06
    emean
    -0.06
    POSITIVE LOGITS
    åįĥå±±
    0.07
     Cum
    0.07
    .radio
    0.07
    é¡·
    0.07
    Cum
    0.07
    POCH
    0.07
    累积
    0.07
    å¼Ĺ鼷
    0.07
    ÑĦиÑĢ
    0.07
    æĹ¥æĸ°æľĪ
    0.07
    Activations Density 0.004%

    No Known Activations