© 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. 31198
    Prev
    Next
    INDEX
    Explanations

    squaring, multiplication, exponentiation

    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
    第ä¸Ģ人
    -0.08
    arios
    -0.08
    éĻĦ表
    -0.07
    æİı
    -0.07
     polic
    -0.07
    社
    -0.07
    -Allow
    -0.07
    .names
    -0.07
    innie
    -0.07
     kurv
    -0.07
    POSITIVE LOGITS
     exponent
    0.11
    æĽ´é«ĺæķĪ
    0.08
     efficiently
    0.08
    å¹Ĥ
    0.07
    åĢįå¢ŀ
    0.07
     efficient
    0.07
    è¾Ĺ转
    0.07
     powers
    0.07
    ponent
    0.06
    æĦļ
    0.06
    Activations Density 0.002%

    No Known Activations