© 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. 37544
    Prev
    Next
    INDEX
    Explanations

    graph or network structures

    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
    Negative Logits
    æĪĸå°ij
    -0.07
    _pref
    -0.07
    shal
    -0.07
    adamente
    -0.07
    ä¸įåIJ«
    -0.07
    éħĿ
    -0.07
     Quỳnh
    -0.07
    uzzi
    -0.07
     внеÑģ
    -0.07
    umin
    -0.07
    POSITIVE LOGITS
    -esque
    0.08
     whose
    0.08
     thá»ķ
    0.07
     analogy
    0.07
    Servers
    0.07
    ijk
    0.07
    -like
    0.07
    èĪ¬çļĦ
    0.07
    åıĸæ°´
    0.07
     wherein
    0.06
    Activations Density 0.030%

    No Known Activations