© 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. 43689
    Prev
    Next
    INDEX
    Explanations

    header context

    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
    uate
    -0.08
    à¸Ĺà¹Į
    -0.08
    fulness
    -0.08
    ishing
    -0.08
    heits
    -0.08
    ners
    -0.07
    niest
    -0.07
    goed
    -0.07
    evity
    -0.07
    SION
    -0.07
    POSITIVE LOGITS
    /footer
    0.10
    aras
    0.08
    aub
    0.08
    alba
    0.08
    hoot
    0.08
    icter
    0.08
    วัล
    0.08
     vitae
    0.08
    less
    0.08
    DidLoad
    0.08
    Activations Density 0.064%

    No Known Activations