© 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. 8251
    Prev
    Next
    INDEX
    Explanations

    swelling or swollen

    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
    icable
    -0.08
    ª
    -0.07
    å°ı妹
    -0.07
    ngle
    -0.07
    ebin
    -0.07
    è¾Ľéħ¸
    -0.07
    身ä½ĵçĬ¶åĨµ
    -0.07
    chte
    -0.07
    zsche
    -0.07
    wis
    -0.07
    POSITIVE LOGITS
    èĦ¹
    0.09
    ä¸īå°º
    0.08
    -headed
    0.08
    èĥĢ
    0.08
    headed
    0.08
     swell
    0.08
    ä½ĵ积
    0.08
    èĨ¨èĥĢ
    0.07
    æĮĩæķ°
    0.07
    èĨ¨
    0.07
    Activations Density 0.066%

    No Known Activations