© 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. 48354
    Prev
    Next
    INDEX
    Explanations

    temporary or transient

    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
     slow
    -0.07
    ç»ıè¿ĩå¤ļå¹´çļĦ
    -0.07
    çĽIJåĴĮ
    -0.07
    æħ¢
    -0.07
    åįĩ级
    -0.06
    slow
    -0.06
    ạp
    -0.06
    æĹ©åľ¨
    -0.06
    åĽº
    -0.06
    åĮĢ
    -0.06
    POSITIVE LOGITS
     temporary
    0.27
    临æŶ
    0.27
     transient
    0.25
    temporary
    0.24
    Temporary
    0.23
     Temporary
    0.23
    Transient
    0.23
     fleeting
    0.22
     ephem
    0.22
    èĩ¨æĻĤ
    0.21
    Activations Density 0.620%

    No Known Activations