© 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. 1755
    Prev
    Next
    INDEX
    Explanations

    special characters followed by units or titles

    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
    iota
    -0.08
    ़
    -0.08
    ield
    -0.08
    à§įস
    -0.08
    huis
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    educt
    -0.08
    ç©Ĥ
    -0.07
    æĹłæŃ¢
    -0.07
    åĪ°ä½İ
    -0.07
    POSITIVE LOGITS
    nya
    0.11
    gether
    0.11
    翼翼
    0.09
    ÑģÑı
    0.09
    ï¸İ
    0.09
    ä¸Ģ
    0.09
    人
    0.09
    ÛĮ
    0.09
    lessly
    0.08
    ten
    0.08
    Activations Density 0.006%

    No Known Activations