© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    l
    -0.07
    la
    -0.07
    è¿Ļä¸Ģ个
    -0.07
    ê¹IJ
    -0.07
    aggio
    -0.07
    اÙĭ
    -0.07
    ley
    -0.06
    à¸ĵà¹Į
    -0.06
    ii
    -0.06
    ÛĮÙĩ
    -0.06
    POSITIVE LOGITS
    æħ·
    0.08
    ingue
    0.08
    çļĦä½ł
    0.08
    人马
    0.08
    å°Ķé¡¿
    0.08
    ernals
    0.08
    schied
    0.07
    velop
    0.07
    çıij
    0.07
    æĸ°éĥ½
    0.07
    Activations Density 0.018%

    No Known Activations