© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    Spanish question marks and exclamation marks

    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
    igrated
    -0.09
    imals
    -0.08
    istet
    -0.08
    .website
    -0.08
    istö
    -0.08
    enticated
    -0.08
    otle
    -0.08
    allocator
    -0.08
    ièrement
    -0.08
    שת
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.09
    ly
    0.09
    ï¸İ
    0.09
    д
    0.08
    d
    0.07
    /how
    0.07
    дÑij
    0.07
     contrario
    0.07
    åħ¶ä¸º
    0.07
    a
    0.07
    Activations Density 0.001%

    No Known Activations