© 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. 13577
    Prev
    Next
    INDEX
    Explanations

    numbers and units (-6.8 dB)

    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
    qu
    -0.08
    quote
    -0.08
    гÑĢад
    -0.07
    é¦
    -0.07
    ä¸ĭæĿ¥çļĦ
    -0.07
    orn
    -0.07
     quot
    -0.07
     Planta
    -0.07
     Kurd
    -0.07
    ÙħاÙĦ
    -0.07
    POSITIVE LOGITS
    orias
    0.10
    oria
    0.07
    å·¥æĪ¿
    0.07
    èĢIJ
    0.07
     leven
    0.07
    hipster
    0.07
    wares
    0.07
    ç«ĭä¿¡
    0.06
    åŀĭåĴĮ
    0.06
    Trust
    0.06
    Activations Density 0.078%

    No Known Activations