© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14152
    Prev
    Next
    INDEX
    Explanations

    2D arrays and matrices

    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°¾
    -0.08
    è¿Ļæł¹
    -0.07
    ä¸Ģ身
    -0.07
     branch
    -0.07
    纶
    -0.07
    è¿ĻæĿ¡
    -0.07
    èĨĬ
    -0.07
     chain
    -0.07
    å°¾éĥ¨
    -0.07
    chain
    -0.07
    POSITIVE LOGITS
    磩éĺµ
    0.12
     matrix
    0.12
    matrix
    0.11
     grid
    0.11
    grid
    0.11
     маÑĤÑĢи
    0.11
     grids
    0.11
    Rows
    0.10
     rows
    0.10
     Rows
    0.10
    Activations Density 0.138%

    No Known Activations