© 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. 22786
    Prev
    Next
    INDEX
    Explanations

    words that modify or follow common articles

    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
    çļĦ使çĶ¨
    -0.06
    ï¼Ī
    -0.06
    (
    -0.06
     ......
    -0.06
     ____
    -0.05
    undu
    -0.05
    ____
    -0.05
    A
    -0.05
    2
    -0.05
    ãĢIJ
    -0.05
    POSITIVE LOGITS
    gte
    0.09
    byt
    0.09
    åijĨåľ¨
    0.09
    ALER
    0.09
    足ä¸įåĩº
    0.08
    RAINT
    0.08
    ahoma
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    /ay
    0.08
    ARIO
    0.08
    Activations Density 0.028%

    No Known Activations