© 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. 18353
    Prev
    Next
    INDEX
    Explanations

    onium or inium compounds

    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
    ability
    -0.08
    éĩij森
    -0.07
    alp
    -0.07
    åĮĸåĴĮ
    -0.07
    ãĥĬãĥ¼
    -0.07
    åĦ¿çļĦ
    -0.07
    enames
    -0.07
    ables
    -0.07
    tem
    -0.07
    åĦ¿
    -0.07
    POSITIVE LOGITS
    imbus
    0.08
    porn
    0.08
    REFERRED
    0.07
    жели
    0.07
    oft
    0.07
    csak
    0.07
    æĬ¢
    0.07
    ycin
    0.07
    ë¹
    0.07
    /black
    0.07
    Activations Density 0.007%

    No Known Activations