© 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. 21228
    Prev
    Next
    INDEX
    Explanations

    storage for items

    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
    举æĿ¯
    -0.08
     Jacuzzi
    -0.07
     interrupted
    -0.07
     Thrones
    -0.07
    èĩªæĿ¥æ°´
    -0.07
    çĴĭ
    -0.07
     ëģĬ
    -0.07
    eler
    -0.07
    ehl
    -0.07
    浴缸
    -0.06
    POSITIVE LOGITS
     contents
    0.14
    _contents
    0.13
    æĶ¶çº³
    0.13
     storing
    0.13
     storage
    0.13
    Contents
    0.13
     Äijá»±ng
    0.12
     Contents
    0.12
    .contents
    0.12
    à¹Ģà¸ģà¹ĩà¸ļ
    0.12
    Activations Density 0.185%

    No Known Activations