© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    at a

    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
    ç³»ç»Łåľ¨
    -0.08
    åįĹèĩ³
    -0.08
    éĽĨåĽ¢åľ¨
    -0.08
    åľ¨è¿Ļæł·çļĦ
    -0.08
    åľ¨çľĭ
    -0.08
    åľ¨çĶ¨
    -0.08
    åľ¨æķĻåѦä¸Ń
    -0.08
    ÑĬÑĤ
    -0.07
    çľ¼ä¸ŃçļĦ
    -0.07
    åľ¨åį³
    -0.07
    POSITIVE LOGITS
     vicinity
    0.10
     whim
    0.09
     ÙĪعÙĨد
    0.09
    ведении
    0.09
     ×ķ×ij
    0.09
     outset
    0.09
     forefront
    0.09
    ÑİÑīем
    0.08
    Ñĩении
    0.08
     extremes
    0.08
    Activations Density 0.440%

    No Known Activations