© 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. 31725
    Prev
    Next
    INDEX
    Explanations

    registered trademarks

    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
    ombat
    -0.09
    коÑĤоÑĢ
    -0.09
    logan
    -0.08
    uggest
    -0.08
    expertise
    -0.08
     academia
    -0.08
     vets
    -0.08
    pike
    -0.08
     feminism
    -0.08
    ×ķ×Ŀ
    -0.08
    POSITIVE LOGITS
     themselves
    0.15
     ones
    0.11
    ä¸Ģ个个
    0.08
    ä¹Łéĥ½æĺ¯
    0.08
    约èĢĮåIJĮ
    0.08
    å®ĥ们æĺ¯
    0.08
     имеÑİÑīие
    0.08
     amelyek
    0.08
    ä¹Łéĥ½
    0.07
    她们çļĦ
    0.07
    Activations Density 0.316%

    No Known Activations