© 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. 30109
    Prev
    Next
    INDEX
    Explanations

    holy, virgin, father, day, light

    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
    ä¿IJ
    -0.09
    ä¸īé«ĺ
    -0.08
    USTA
    -0.08
     Javas
    -0.08
    аÑĤо
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    æĬĸ
    -0.07
    ynchronously
    -0.07
    heil
    -0.07
    gau
    -0.07
    POSITIVE LOGITS
     âĢ¦
    0.11
    âĢ¦âĢ¦
    0.10
     [
    0.09
     (âĢ¦)
    0.08
     ...
    0.08
     [âĢ¦]
    0.08
     [...]
    0.08
    èĻı
    0.07
    ä¸įåı¯ä»¥
    0.07
    âĢ¦
    0.07
    Activations Density 0.009%

    No Known Activations