© 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. 57884
    Prev
    Next
    INDEX
    Explanations

    common or popular words

    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
    ostr
    -0.09
    å¦Ĥä¸Ģ
    -0.08
    áf
    -0.08
    ierge
    -0.08
    è¿ĻäºĽåĽłç´ł
    -0.07
    -than
    -0.07
    äºĽè®¸
    -0.07
    chino
    -0.07
    klin
    -0.07
    æľĢç¾İ好çļĦ
    -0.07
    POSITIVE LOGITS
     popular
    0.08
    åı¯æĺ¯ä»ĸ
    0.08
    çļĦç¡®æĺ¯
    0.08
    人ä¹ĭ
    0.08
     commonly
    0.08
     common
    0.08
    åı¯æĺ¯åľ¨
    0.08
     ë¶Ħëªħ
    0.07
     widely
    0.07
    ç¡®å®ŀæĺ¯
    0.07
    Activations Density 0.016%

    No Known Activations