© 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. 57055
    Prev
    Next
    INDEX
    Explanations

    suspension, cancellation, end

    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
    çĿĢäºĨ
    -0.08
    yac
    -0.07
    ombs
    -0.07
     ÑģквозÑĮ
    -0.07
    guide
    -0.07
    åĸľæĢĴ
    -0.07
    quest
    -0.06
    .datab
    -0.06
    chema
    -0.06
    quis
    -0.06
    POSITIVE LOGITS
    äºĨä¸ĢåĪĩ
    0.10
    ä¸įäºĨçļĦ
    0.10
    äºĨ对
    0.09
     hẳn
    0.09
    /disable
    0.09
    ible
    0.09
    ä¸įä¹ħçļĦ
    0.09
    ä¸įäºĨ
    0.09
    äºĨçļĦ
    0.09
    ÛĮÙĩ
    0.08
    Activations Density 0.078%

    No Known Activations