© 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. 48237
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    /trunk
    -0.07
    adat
    -0.07
    ür
    -0.07
    duct
    -0.07
    itto
    -0.07
    ician
    -0.07
    nette
    -0.07
    и
    -0.07
     dank
    -0.07
    殿ä¸ĭ
    -0.07
    POSITIVE LOGITS
    zens
    0.07
    yac
    0.07
     Arena
    0.07
    à¸Ńà¸Ļุ
    0.07
    ä¸īæľĪ
    0.07
    ä¸īåŃĹ
    0.07
    erialized
    0.06
    ستاÙĨ
    0.06
    ä¸īæĹ¥
    0.06
    rof
    0.06
    Activations Density 0.005%

    No Known Activations