© 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. 45206
    Prev
    Next
    INDEX
    Explanations

    matrix

    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
    æĭĻ
    -0.06
    çŃĴ
    -0.06
    eting
    -0.06
     Miet
    -0.06
    arya
    -0.06
    tesi
    -0.06
    ce
    -0.06
    åĵ®
    -0.06
     길
    -0.06
    /devices
    -0.06
    POSITIVE LOGITS
    磩éĺµ
    0.17
     matrix
    0.17
     Matrix
    0.15
    matrix
    0.15
    _matrix
    0.15
     matrices
    0.14
    Matrix
    0.14
     маÑĤÑĢи
    0.14
     matriz
    0.13
     MATRIX
    0.13
    Activations Density 0.048%

    No Known Activations