© 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. 10350
    Prev
    Next
    INDEX
    Explanations

    solve linear equations and systems

    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
    å±¥
    -0.08
    imiter
    -0.08
    ervas
    -0.08
    olat
    -0.08
    壽
    -0.08
     Bán
    -0.07
    .addProperty
    -0.07
    erval
    -0.07
    acson
    -0.07
    寿
    -0.07
    POSITIVE LOGITS
    解
    0.11
    æ±Ĥ解
    0.10
     solve
    0.09
     solved
    0.09
     solving
    0.09
     solution
    0.09
     overd
    0.09
    solve
    0.09
     Solve
    0.09
     solutions
    0.09
    Activations Density 0.045%

    No Known Activations