© 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. 13322
    Prev
    Next
    INDEX
    Explanations

    one in five

    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
    odb
    -0.09
     Giunta
    -0.08
    èĢĮè¿Ļç§į
    -0.08
    æĺµ
    -0.07
    icca
    -0.07
    èī¾çijŀ
    -0.07
    erras
    -0.07
    /back
    -0.07
    енÑģа
    -0.07
    水份
    -0.07
    POSITIVE LOGITS
    代表
    0.07
    驼
    0.06
     represent
    0.06
    çļĦ代表
    0.06
    æľ¦
    0.06
    æĦīæĤ¦
    0.06
    æłĩçļĦ
    0.06
    å¹½
    0.06
     represents
    0.06
     Represent
    0.06
    Activations Density 0.094%

    No Known Activations