© 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. 14937
    Prev
    Next
    INDEX
    Explanations

    relu

    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
    èĢĮ论
    -0.08
    家äºĭ
    -0.07
    ntag
    -0.07
    ä¸įå°ijç½ijåıĭ
    -0.07
     subsid
    -0.07
    .nih
    -0.07
    ocz
    -0.07
    .qq
    -0.07
    Õ·
    -0.07
     gram
    -0.07
    POSITIVE LOGITS
     softmax
    0.08
    ReLU
    0.08
     activations
    0.08
    lient
    0.07
    relu
    0.07
    alsy
    0.07
    ìĤ°
    0.07
    软
    0.07
     Neuroscience
    0.07
    åľ£
    0.06
    Activations Density 0.006%

    No Known Activations