© 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. 50324
    Prev
    Next
    INDEX
    Explanations

    graphs of physical quantities

    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
    elis
    -0.08
    este
    -0.07
    çľ¼èĬ±ç¼Ńä¹±
    -0.07
    thon
    -0.06
    åĿĤ
    -0.06
    rove
    -0.06
    ovid
    -0.06
    æ´Ľä¼Ĭ
    -0.06
    utel
    -0.06
    宿
    -0.06
    POSITIVE LOGITS
     plotted
    0.09
    Plot
    0.08
    è¶Ĭ好
    0.07
    ìĪĺë¡Ŀ
    0.07
    ä¼ļåIJĮ
    0.07
    åľ¨æ¯ı个
    0.07
     normalized
    0.07
    cz
    0.07
    éļıçĿĢæŶéĹ´çļĦ
    0.07
    Normalized
    0.07
    Activations Density 0.024%

    No Known Activations