© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60079
    Prev
    Next
    INDEX
    Explanations

    cube root and derivatives

    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
     Tenggara
    -0.10
    elah
    -0.08
    arau
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    ayed
    -0.08
    Instances
    -0.08
    heen
    -0.08
    亦ä¹IJä¹İ
    -0.07
    ::$
    -0.07
    лам
    -0.07
    POSITIVE LOGITS
    液ä½ĵ
    0.07
    æĮª
    0.06
    Ĭ
    0.06
    液ä½ĵçļĦ
    0.06
    éĩijé¾Ļ
    0.06
     Trouble
    0.06
    ä¸įçĿĢ
    0.06
    Reality
    0.06
    ê·ł
    0.06
    åıĺå½¢
    0.06
    Activations Density 0.002%

    No Known Activations