© 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. 9609
    Prev
    Next
    INDEX
    Explanations

    LEFT JOIN

    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
    ,
    -0.08
    u
    -0.08
     "*",
    -0.07
    eming
    -0.07
    ij¸
    -0.06
    åħ¨ä½ĵ人åijĺ
    -0.06
    ç¼¥
    -0.06
    ä¸ŃæĪIJéķ¿
    -0.06
    ules
    -0.06
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.06
    POSITIVE LOGITS
    ievo
    0.09
    :description
    0.08
    ÙĨÙĩ
    0.08
    æĢªä¸įå¾Ĺ
    0.08
    iers
    0.08
    antum
    0.08
    大åĪ°
    0.07
    øre
    0.07
    iese
    0.07
    æĮģä¹ĭ以
    0.07
    Activations Density 0.004%

    No Known Activations