© 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. 51168
    Prev
    Next
    INDEX
    Explanations

    miniport adapters, prime number

    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
    etwork
    -0.09
    leck
    -0.08
     Gradu
    -0.07
    ê¸ī
    -0.07
    stead
    -0.07
    æĩ
    -0.07
    á»ıng
    -0.07
     leck
    -0.07
    eci
    -0.07
    èĩªå·±çļĦå·¥ä½ľ
    -0.07
    POSITIVE LOGITS
    åĽº
    0.08
    客
    0.07
    å®ŀ
    0.07
     riv
    0.07
    åĴĮä¸Ģ
    0.06
    ÙĪÙĬس
    0.06
    客æ°Ķ
    0.06
    iland
    0.06
     Alves
    0.06
     Andres
    0.06
    Activations Density 0.107%

    No Known Activations