© 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. 55682
    Prev
    Next
    INDEX
    Explanations

    magnitude, length, scale, speed, profit

    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
    ساÙĨ
    -0.08
    æĦıä¹īéĩį大
    -0.08
    æĹłéĿŀ
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.07
     afer
    -0.07
    kir
    -0.07
    æķ°éĩıæľīéĻIJ
    -0.07
    请çĻ»å½ķ
    -0.07
    并éĿŀ
    -0.07
    ors
    -0.07
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.08
    以åıĬåľ¨
    0.08
    æĺ¯å¤ļå°ij
    0.08
    åľ¨æŃ¤æ¬¡
    0.08
     ÙĪÙĥÙĬÙģ
    0.08
    hra
    0.07
    äºĨå¤ļå°ij
    0.07
    æĺ¯åĵª
    0.07
    æľīå¤ļå°ij
    0.07
    (es
    0.07
    Activations Density 0.061%

    No Known Activations