© 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. 43104
    Prev
    Next
    INDEX
    Explanations

    relevance and comparison aspects

    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
    arkin
    -0.07
    enza
    -0.07
    arana
    -0.07
    atina
    -0.06
    dden
    -0.06
    kunde
    -0.06
    ed
    -0.06
    åĪĢçļĦ
    -0.06
    .di
    -0.06
    身影
    -0.06
    POSITIVE LOGITS
    综åIJĪè¯Ħä»·
    0.08
    обÑĢа
    0.08
    ä¼ĺåĬ£
    0.08
    ahi
    0.08
    èĦ±é¢ĸèĢĮåĩº
    0.07
    æĿľ
    0.07
     pén
    0.07
    theless
    0.07
    igor
    0.07
    ç´
    0.07
    Activations Density 0.005%

    No Known Activations