© 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. 40690
    Prev
    Next
    INDEX
    Explanations

    noble gases, Ar, Ne

    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
    ories
    -0.06
    æŃ£æīĢè°ĵ
    -0.06
    à¤Ĺà¥įर
    -0.06
    viel
    -0.06
    æ³¥æ³ŀ
    -0.06
     lâm
    -0.06
    ikli
    -0.06
     parch
    -0.06
    uly
    -0.06
    tar
    -0.06
    POSITIVE LOGITS
     gases
    0.10
    ä¸įåıĤä¸İ
    0.09
    åİŁåŃIJ
    0.08
    æ°Ķä½ĵ
    0.08
    riott
    0.08
    /perl
    0.08
    æ°ĶçļĦ
    0.08
    aston
    0.08
    à¸ķà¸Ļ
    0.08
    æ°Ķ
    0.08
    Activations Density 0.013%

    No Known Activations