© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    speculation about mathematical formulas

    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
    Negative Logits
    ++,
    -0.08
    RELATED
    -0.07
    mue
    -0.07
     thầm
    -0.07
    *M
    -0.07
    ’B
    -0.07
    watan
    -0.07
    ibo
    -0.07
    ael
    -0.07
    !),
    -0.07
    POSITIVE LOGITS
    è¯Ŀ说
    0.07
    ewan
    0.07
     (âĢ¦)
    0.07
     [...]
    0.06
    ãĥ©ãĥ³ãĤ¹
    0.06
    Ù°
    0.06
     Eta
    0.06
    éĹ´çļĦ
    0.06
    ÑģиÑı
    0.06
    liess
    0.06
    Activations Density 0.008%

    No Known Activations