© 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. 32917
    Prev
    Next
    INDEX
    Explanations

    non-english character sequences

    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
    athan
    -0.07
    âĦ
    -0.06
    InBackground
    -0.06
     Lair
    -0.06
    brook
    -0.06
    PHA
    -0.06
     Brief
    -0.06
     Elk
    -0.06
    voir
    -0.06
    _UNUSED
    -0.06
    POSITIVE LOGITS
    imps
    0.07
    åIJĦç§įåIJĦæł·
    0.07
    俱ä¹IJéĥ¨
    0.07
    ÑħаÑħ
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    ìĹIJìļĶ
    0.07
    osu
    0.07
    à±ģ
    0.07
    eded
    0.07
    otyping
    0.07
    Activations Density 0.005%

    No Known Activations