© 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. 64713
    Prev
    Next
    INDEX
    Explanations

    constant pressure or external force

    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
    缩水
    -0.08
     dzi
    -0.07
    /Delete
    -0.07
    eltas
    -0.07
    å½¢å¼ıçļĦ
    -0.07
    éné
    -0.07
    ãģ£ãģĿ
    -0.07
    è½´è·Ŀ
    -0.07
    -hide
    -0.07
     quartiere
    -0.07
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.09
     external
    0.08
    ohn
    0.08
    External
    0.08
    external
    0.08
     External
    0.08
    åĮ¹éħį
    0.07
    å¤ĸéĿ¢
    0.07
     externally
    0.07
     constantly
    0.07
    Activations Density 0.003%

    No Known Activations