© 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. 63459
    Prev
    Next
    INDEX
    Explanations

    Vector Field

    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
    æľĿ天
    -0.08
    дела
    -0.07
    ãĥĥãĤ·ãĥ³ãĤ°
    -0.07
    æĹºéĵº
    -0.07
    Į¨
    -0.07
    ä¹ĭ交
    -0.06
    æĹłæĢ¨
    -0.06
    Lang
    -0.06
    ìĬ¤íĦ°
    -0.06
    hev
    -0.06
    POSITIVE LOGITS
    åĬłæĿĥ
    0.09
     weighted
    0.08
    æĿĥ
    0.07
    æ±°
    0.07
    æľ¬
    0.07
    weighted
    0.07
    .define
    0.07
    æ²ī
    0.07
    >{$
    0.07
     Weight
    0.07
    Activations Density 0.013%

    No Known Activations