© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37786
    Prev
    Next
    INDEX
    Explanations

    restriction enzyme sites

    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
    upil
    -0.08
    orio
    -0.08
    举åĬ¨
    -0.07
    äºĶå®ĺ
    -0.07
     hott
    -0.07
    abouts
    -0.07
    é¾Ļæ³ī
    -0.07
    CTest
    -0.07
    ciuto
    -0.07
    umer
    -0.06
    POSITIVE LOGITS
    åĪĩåī²
    0.09
     fragment
    0.08
    endon
    0.08
    ä¸įæŃ»
    0.07
    ENDER
    0.07
     fragments
    0.07
     cuts
    0.07
     Fragment
    0.07
    _sites
    0.07
     release
    0.07
    Activations Density 0.021%

    No Known Activations