© 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. 61899
    Prev
    Next
    INDEX
    Explanations

    counted as

    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
    er
    -0.09
    ities
    -0.08
    à±į
    -0.08
    ×Ļ׳×ķ
    -0.08
    ious
    -0.08
    eram
    -0.07
    Å¡Å¥
    -0.07
    idl
    -0.07
    ÒĻ
    -0.07
    á»ħu
    -0.07
    POSITIVE LOGITS
    åĦ¿çļĦ
    0.11
    å¾Ĺä¸Ĭ
    0.10
    itude
    0.10
    åį³éĢĿ
    0.09
    0.08
    Ø©
    0.08
    ed
    0.08
    بطاÙĦ
    0.08
    ราà¸Ĭà¸ģาร
    0.08
    niest
    0.08
    Activations Density 0.001%

    No Known Activations