© 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. 60906
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code elements

    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
    _qual
    -0.06
    änä
    -0.06
    ÑħÑĸд
    -0.06
    ahari
    -0.06
    åĽ½ç¨İ
    -0.06
    大èĢĮ
    -0.06
    odon
    -0.05
     Dek
    -0.05
    ä¸įçľĭ
    -0.05
    åĮĹå¸Ĥ
    -0.05
    POSITIVE LOGITS
    singleton
    0.08
     corresponding
    0.08
    峪
    0.08
    代表
    0.08
     représentant
    0.08
    对åºĶçļĦ
    0.08
    .swap
    0.08
    mlin
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    对åºĶ
    0.08
    Activations Density 0.016%

    No Known Activations