© 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. 41391
    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
    好好çļĦ
    -0.07
    æľĢåIJİçĻ»å½ķ
    -0.07
    Ĩµ
    -0.06
     Charlottesville
    -0.06
     obv
    -0.06
    ¬ģ
    -0.06
    毫æĹłçĸijéĹ®
    -0.06
    尼迪
    -0.06
    èĢĮ以
    -0.06
     Pulitzer
    -0.06
    POSITIVE LOGITS
     Gale
    0.07
    alendar
    0.07
    ziv
    0.07
    åħ±äº§åħļåijĺ
    0.07
    æŀĹçļĦ
    0.07
     mira
    0.07
    ffset
    0.07
    群çļĦ
    0.07
    iset
    0.06
    elib
    0.06
    Activations Density 0.337%

    No Known Activations