© 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. 32425
    Prev
    Next
    INDEX
    Explanations

    independent and scale-free properties

    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
    æĪijæĦ¿æĦı
    -0.07
    عÙĩد
    -0.07
     fran
    -0.07
    æ¸Ŀ
    -0.07
     Studium
    -0.07
    åħ¼ãģŃ
    -0.07
    éĿ¢åIJij
    -0.07
    æł©æł©
    -0.07
    aul
    -0.06
    hammer
    -0.06
    POSITIVE LOGITS
    æĹłåħ³
    0.08
    éĻ¤äºĨåľ¨
    0.07
    anity
    0.07
    QG
    0.07
    jsc
    0.07
    主è¦ģä½ĵçİ°åľ¨
    0.07
    ä½ĵçİ°åľ¨
    0.06
     involvement
    0.06
    éľ
    0.06
    alak
    0.06
    Activations Density 0.009%

    No Known Activations