© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3255
    Prev
    Next
    INDEX
    Explanations

    awning success

    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
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    åĴĮæĹł
    -0.08
    æĻĵ举
    -0.07
    alise
    -0.07
     NONE
    -0.07
    å°ıéĽª
    -0.07
    æĨĶ
    -0.07
    ä¸īé«ĺ
    -0.07
    ç»ĩ女
    -0.07
    aket
    -0.07
    POSITIVE LOGITS
    zis
    0.07
    getic
    0.07
    ysin
    0.07
    æĬķ
    0.07
    æĶ¶
    0.07
    çİ°ä½ı
    0.07
    Õ¡Õ¿
    0.06
    åĵ¥
    0.06
    гоÑĤ
    0.06
    белÑĮ
    0.06
    Activations Density 0.002%

    No Known Activations