© 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. 22381
    Prev
    Next
    INDEX
    Explanations

    suffix "-tion" or proper nouns in document titles

    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
    iace
    -0.07
    èĢĮä¸Ķè¦ģ
    -0.06
    æĶĢ
    -0.06
    人æ°ijåħ±åĴĮåĽ½
    -0.06
     dime
    -0.06
    _unix
    -0.06
     diras
    -0.06
    .Xaml
    -0.06
    ni
    -0.06
    heet
    -0.06
    POSITIVE LOGITS
    RIES
    0.08
    æĢ»åĢ¼
    0.08
    ubar
    0.08
    åĪ
    0.08
     cancelling
    0.07
    arana
    0.07
    天河
    0.07
    illis
    0.07
    åĩıçģ¾
    0.07
    ammans
    0.07
    Activations Density 0.001%

    No Known Activations