© 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. 61710
    Prev
    Next
    INDEX
    Explanations

    medical suffixes

    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
    enburg
    -0.08
    çī¹æĸ¯
    -0.08
    å¤įåĪ¶éĵ¾æİ¥
    -0.08
    çļĦæŶåĢĻåı¯ä»¥
    -0.08
    ÑĬ
    -0.08
    æľĪ份å¼Ģå§ĭ
    -0.08
    COMPARE
    -0.08
    å¾ħç»Ń
    -0.08
    æĤ¨å½ĵåīįçļĦ
    -0.08
    æĪij们ä¼ļ尽快
    -0.08
    POSITIVE LOGITS
    ç®Ģ称
    0.07
    или
    0.07
    lest
    0.06
    以åıĬ
    0.06
    ilit
    0.06
    åıĬåħ¶
    0.06
    اتÙĬ
    0.06
    inten
    0.06
    /*
    0.06
     (
    0.05
    Activations Density 1.379%

    No Known Activations