© 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. 48366
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    Ń
    -0.07
    éĸĵ
    -0.07
    éĹ´
    -0.06
    mane
    -0.06
    éĸĵãģ¯
    -0.06
    éĺ³æĺ¥
    -0.06
    ½
    -0.06
    amic
    -0.06
    dni
    -0.06
    ä¸įä¹ħ
    -0.06
    POSITIVE LOGITS
    ogui
    0.07
    ToFront
    0.07
     Sehat
    0.07
    adini
    0.07
    æĪijçļĦçľĭæ³ķ
    0.07
    åIJĮæŃ¥
    0.07
     convincing
    0.07
    åľ¨åľ°
    0.07
    à¸ģระà¸Ĺ
    0.07
    amb
    0.07
    Activations Density 0.002%

    No Known Activations