© 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. 59120
    Prev
    Next
    INDEX
    Explanations

    mathematical constraints

    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
    ushman
    -0.08
    ogna
    -0.08
    åľ¨åģļ好
    -0.07
    ç²ĭ
    -0.07
    cide
    -0.07
    asco
    -0.06
    ObjectContext
    -0.06
    æľ¬ç«ĻåĨħ容
    -0.06
    åĪ©çī©
    -0.06
    .stem
    -0.06
    POSITIVE LOGITS
    约æĿŁ
    0.10
     constraint
    0.10
     Constraint
    0.10
    é½
    0.09
     constraints
    0.09
    Constraint
    0.09
    _constraint
    0.08
     Constraints
    0.08
    .Constraint
    0.08
    .constraint
    0.08
    Activations Density 0.008%

    No Known Activations