© 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. 48640
    Prev
    Next
    INDEX
    Explanations

    direction or opposition

    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
    主ä½ĵçļĦ
    -0.07
    entos
    -0.07
     incor
    -0.07
    ä¸įä»İ
    -0.07
    æĪĸå°ı
    -0.07
    Ŀ
    -0.06
    æľ¬è´¨
    -0.06
    çļĦ主ä½ĵ
    -0.06
    主ä½ĵ
    -0.06
     Heid
    -0.06
    POSITIVE LOGITS
    æľ¬æĸĩéĵ¾æİ¥
    0.08
     Expos
    0.08
    å½¢æĪIJäºĨä¸Ģ个
    0.08
    kniÄĻ
    0.08
    leston
    0.07
    tesi
    0.07
    æĸ¹ä½į
    0.07
     Empfang
    0.07
    WISE
    0.07
    exposition
    0.07
    Activations Density 0.021%

    No Known Activations