© 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. 20374
    Prev
    Next
    INDEX
    Explanations

    defending champions

    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
    ланд
    -0.07
    æĦŁçŁ¥
    -0.07
    è¿ijè·Ŀ离
    -0.07
    åIJĽå®ī
    -0.07
    计æŶ
    -0.07
    kest
    -0.07
    erei
    -0.06
    IFY
    -0.06
    æľ¯
    -0.06
    ÑħодиÑĤ
    -0.06
    POSITIVE LOGITS
    æľŁåĪĿ
    0.10
    æľ¬å¹´
    0.07
    aval
    0.07
    æľŁæľ«
    0.07
    /new
    0.07
    æĸ°æŧ
    0.07
    åį§é¾Ļ
    0.07
    æŧ
    0.07
    new
    0.07
     Beginning
    0.07
    Activations Density 0.005%

    No Known Activations