© 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. 29900
    Prev
    Next
    INDEX
    Explanations

    listing numbers and punctuation

    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
    ixe
    -0.07
    家æĺ¯
    -0.07
    dbe
    -0.07
     ours
    -0.07
    uire
    -0.07
    ÑĦоÑĢма
    -0.07
    åŃIJæĺ¯
    -0.06
    éĹ®é¢ĺæĺ¯
    -0.06
    èįIJ
    -0.06
    åŃIJãģ¯
    -0.06
    POSITIVE LOGITS
    åĿŀ
    0.08
    oret
    0.08
    æĿ¯éħĴ
    0.07
    ä»ĸèĩªå·±çļĦ
    0.07
    æĺĬ天
    0.07
     rakel
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    IPA
    0.07
    ï¸ı
    0.07
    ärt
    0.07
    Activations Density 0.085%

    No Known Activations