© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    boundary conditions

    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
    aeda
    -0.08
    edm
    -0.07
    æĬ¡
    -0.07
    afari
    -0.07
    odash
    -0.07
    éĹ´éļĻ
    -0.07
    çļĦæĪIJåĪĨ
    -0.07
     hüb
    -0.06
    åŃ°
    -0.06
    ä¸īå®Ŀ
    -0.06
    POSITIVE LOGITS
     boundary
    0.14
    è¾¹çķĮ
    0.13
     Boundary
    0.12
    boundary
    0.12
    Boundary
    0.11
     boundaries
    0.11
    oundary
    0.10
     constraints
    0.10
    _boundary
    0.10
    约æĿŁ
    0.09
    Activations Density 0.018%

    No Known Activations