© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parenthesis or random

    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
    æī¿
    -0.07
    precated
    -0.06
     nghá»ī
    -0.06
     Ortega
    -0.06
     bearing
    -0.06
    GCC
    -0.06
    ưỡng
    -0.06
    SRC
    -0.06
    为建设
    -0.05
    engel
    -0.05
    POSITIVE LOGITS
    ç²¾ç¥ŀä¸ĬçļĦ
    0.07
    elok
    0.07
    è°ħ
    0.07
    OfClass
    0.07
    meer
    0.07
    çĸ¾
    0.07
    åİ
    0.07
     spi
    0.07
    antin
    0.07
    ↵     ↵
    0.07
    Activations Density 0.083%

    No Known Activations