© 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. 57984
    Prev
    Next
    INDEX
    Explanations

    matrix and linear algebra concepts

    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
    à®Łà¯įà®ļ
    -0.08
    åį³éĢĿ
    -0.08
    èľĴ
    -0.07
    æĤł
    -0.07
    å·¥åķĨæĪ·
    -0.07
     chant
    -0.07
    scriber
    -0.07
     Gallagher
    -0.07
    æ°Ľ
    -0.07
    åIJ¸åħ¥
    -0.07
    POSITIVE LOGITS
     matrices
    0.16
    磩éĺµ
    0.16
     matrix
    0.15
    matrix
    0.14
     маÑĤÑĢи
    0.13
     matriz
    0.13
    .matrix
    0.13
     transpose
    0.12
    Matrix
    0.12
     Matrix
    0.12
    Activations Density 0.064%

    No Known Activations