© 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. 23184
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    Ĵ
    -0.08
    ä¹ĭå®Ŀ
    -0.07
    å°ıæĿ¿
    -0.07
    au
    -0.07
    ech
    -0.06
    ale
    -0.06
     cara
    -0.06
    æݧèĤ¡åŃIJåħ¬åı¸
    -0.06
    ä¸įè¦ģ被
    -0.06
    Ùģ
    -0.06
    POSITIVE LOGITS
    slaught
    0.08
    lew
    0.07
    uvi
    0.07
    æĮij
    0.07
     rectific
    0.07
    ä¸ĥä¸ĥ
    0.07
    .dispatcher
    0.07
    %%%%%%%%
    0.07
    uxt
    0.06
    èĮ¨
    0.06
    Activations Density 0.121%

    No Known Activations