© 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. 10941
    Prev
    Next
    INDEX
    Explanations

    Objective-C framework classes

    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
    æŶéĹ´åľ¨
    -0.09
    çĤ¹åľ¨
    -0.08
    åĮĸå¤ĦçIJĨ
    -0.08
    å¹´åľ¨
    -0.08
    æľĪåľ¨
    -0.08
    ull
    -0.07
    çļĦäººåľ¨
    -0.07
    人ä¼ļ
    -0.07
    enc
    -0.07
    人åİ»
    -0.07
    POSITIVE LOGITS
    ä¸Ń
    0.09
    ä¸ŃåĴĮ
    0.08
    æĺ¯æŶåĢĻ
    0.08
    Ùĭا
    0.08
    ä¸Ń以
    0.08
     Ú©ÛIJ
    0.08
    ricos
    0.07
    nya
    0.07
    ä¸Ńãģ§
    0.07
    éĩĮ
    0.07
    Activations Density 0.025%

    No Known Activations