© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    defense or defence

    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
    émie
    -0.08
    gether
    -0.08
    оеди
    -0.08
    taus
    -0.07
    keit
    -0.07
    åı¯å¾ª
    -0.07
    keiten
    -0.07
    æł·çļĦ
    -0.07
    ohan
    -0.07
    _except
    -0.07
    POSITIVE LOGITS
    able
    0.09
     against
    0.09
    iveness
    0.09
    lessness
    0.09
     Against
    0.09
    åıįåĩ»
    0.08
    ä¸į严
    0.08
    against
    0.08
    less
    0.08
    ese
    0.08
    Activations Density 0.031%

    No Known Activations