© 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. 58809
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and definitions

    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
    abil
    -0.09
    æľ¬çīĩ
    -0.09
     Apt
    -0.09
    anser
    -0.09
    é¾Ļæ¹¾
    -0.08
    бÑĢÑı
    -0.08
    /apt
    -0.08
    çłĶ究ä¼ļ
    -0.08
    .«
    -0.08
    æŶéĹ´åľ¨
    -0.08
    POSITIVE LOGITS
    ena
    0.08
    ãĤµãĥ©
    0.07
     trivial
    0.07
    æ
    0.07
     mens
    0.06
    ness
    0.06
    è§
    0.06
     ör
    0.06
    羡
    0.06
    èķ´
    0.05
    Activations Density 0.005%

    No Known Activations