© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    October pink

    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
    arges
    -0.08
    æ·Ģ
    -0.07
    ÑĢÑĤи
    -0.07
    minster
    -0.07
    ä»Ķ
    -0.07
    Ý
    -0.07
    hofer
    -0.07
    KAN
    -0.07
    chsel
    -0.07
    gart
    -0.07
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.07
    为äºĨ让
    0.07
    éĹ
    0.07
    мÑı
    0.07
    .signal
    0.06
    为äºĨå®ŀçİ°
    0.06
    åĨ¥
    0.06
    ance
    0.06
    æĺ¯ä¸ºäºĨ
    0.06
    arend
    0.06
    Activations Density 0.116%

    No Known Activations