© 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. 32373
    Prev
    Next
    INDEX
    Explanations

    numbers, counts, and quantities

    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
    ä»İ严
    -0.07
    ä¸Ģèĩ´
    -0.06
     presentation
    -0.06
    .convert
    -0.06
    ç½¹
    -0.06
    åħ¨æł¡å¸ĪçĶŁ
    -0.06
     Medal
    -0.06
    åijĪçİ°åľ¨
    -0.06
    resh
    -0.06
     présentation
    -0.06
    POSITIVE LOGITS
     strategically
    0.10
    è¦ĨçĽĸäºĨ
    0.10
     sufficient
    0.09
    è¦ĨçĽĸéĿ¢
    0.09
    Coverage
    0.09
     covering
    0.08
     covers
    0.08
    ä¸ĩèĥ½
    0.08
     Coverage
    0.08
    covers
    0.08
    Activations Density 0.014%

    No Known Activations