© 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. 48261
    Prev
    Next
    INDEX
    Explanations

    çļĦ and ãģ®

    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
    à¹īà¸Ńม
    -0.07
    æĺ¯åIJ¦
    -0.06
    uns
    -0.06
    udd
    -0.06
    é«ĺé¢ij
    -0.06
    nick
    -0.06
    é«ĺé«ĺ
    -0.06
    ä¹ĥèĩ³
    -0.06
    º
    -0.06
    ibern
    -0.06
    POSITIVE LOGITS
    çĿĢåij¢
    0.10
    çļĦèĥĮåIJİ
    0.10
    ç¼ĺæķħ
    0.09
    çļĦç¼ĺæķħ
    0.09
    rys
    0.09
    æŶåĢĻ
    0.09
    ä½łçŁ¥éģĵåIJĹ
    0.08
    缸åħ³æݨèįIJ
    0.08
    allon
    0.08
    æĻĤåĢĻ
    0.08
    Activations Density 0.005%

    No Known Activations