© 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. 16245
    Prev
    Next
    INDEX
    Explanations

    matrix factorization, metalloproteinases, variate

    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
    empt
    -0.08
    rious
    -0.08
    coming
    -0.08
    sworth
    -0.07
    isman
    -0.07
    orno
    -0.07
    ارض
    -0.07
     جدÙĭا
    -0.07
    mark
    -0.07
    gers
    -0.07
    POSITIVE LOGITS
    bauer
    0.09
    /vector
    0.09
    rices
    0.09
    Ø©
    0.09
    ially
    0.08
    etje
    0.08
    /array
    0.08
    ÑĢÑĮ
    0.08
    plotlib
    0.08
    ériel
    0.08
    Activations Density 0.037%

    No Known Activations