© 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. 38818
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é¾Ħ
    -0.07
    ç©·
    -0.07
     mas
    -0.06
    ksi
    -0.06
    迹
    -0.06
    éģį
    -0.06
    æļ´éľ²
    -0.06
    è·Ŀ离
    -0.06
    æ¯
    -0.06
    icin
    -0.06
    POSITIVE LOGITS
    RESS
    0.08
    å¼ķ人åħ¥
    0.07
    .gca
    0.07
    oning
    0.07
    æIJŀ
    0.07
    etting
    0.07
    æĪIJ家
    0.07
    ondes
    0.07
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.07
    ç¯ĩä¸Ģ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.