© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20661
    Prev
    Next
    INDEX
    Explanations

    matrix or array 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
    ifik
    -0.09
    rast
    -0.08
    æĢ§åľ°
    -0.07
    eben
    -0.07
    а
    -0.07
    ои
    -0.07
    ovala
    -0.07
    اÙĭ
    -0.07
    å§ij
    -0.07
    idades
    -0.07
    POSITIVE LOGITS
    soever
    0.07
    <![
    0.07
    ¢
    0.07
    .setter
    0.07
    (Expected
    0.07
     laba
    0.07
    大è¯Ŀ
    0.07
    ï¸İ
    0.06
    Heroes
    0.06
    зел
    0.06
    Activations Density 0.002%

    No Known Activations