© 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. 7463
    Prev
    Next
    INDEX
    Explanations

    mathematical constraints and solvers

    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
    oom
    -0.08
     redraw
    -0.07
    ateau
    -0.07
    äum
    -0.07
    Ö¸
    -0.07
    blings
    -0.07
    udel
    -0.07
    bron
    -0.07
    athing
    -0.07
    ket
    -0.07
    POSITIVE LOGITS
     constraints
    0.09
    Constraints
    0.08
     coefficients
    0.08
     Constraints
    0.08
     matrices
    0.07
    å¾ħå®ļ
    0.07
    约æĿŁ
    0.07
    Solver
    0.07
     Orth
    0.07
    _constraints
    0.07
    Activations Density 0.007%

    No Known Activations