© 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. 48762
    Prev
    Next
    INDEX
    Explanations

    protection and being protected

    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
    -0.09
    atures
    -0.08
    ities
    -0.07
    ÙĪÛĮÙĩ
    -0.07
    plorer
    -0.07
    veau
    -0.07
    olph
    -0.07
    kerja
    -0.07
    upati
    -0.07
    ÙĩÙĪØ©
    -0.07
    POSITIVE LOGITS
    ively
    0.10
    iveness
    0.09
     diri
    0.09
    åħįåıĹ
    0.08
    à¸Ħุà¹īมà¸Ħรà¸Ńà¸ĩ
    0.08
    ä¼ŀ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    isson
    0.08
    ä¸įä½ı
    0.08
    TECTED
    0.08
    Activations Density 0.044%

    No Known Activations