© 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. 61798
    Prev
    Next
    INDEX
    Explanations

    type or kind

    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
     (!((
    -0.07
    ä¸įçĿĢ
    -0.07
    é¾Ļäºķ
    -0.07
    éĢ¢
    -0.06
    ä¸įå½Ĵ
    -0.06
    åĭķæħĭ
    -0.06
    èĶ·
    -0.06
    UTE
    -0.06
    åIJį为
    -0.06
    mits
    -0.06
    POSITIVE LOGITS
    ç§įç±»
    0.12
     type
    0.12
    ç±»åŀĭ
    0.11
    ç§įç±»çļĦ
    0.11
    type
    0.10
    種é¡ŀ
    0.10
    çļĦç§įç±»
    0.10
    jenis
    0.10
    /type
    0.10
    ç±»åĪ«
    0.09
    Activations Density 0.140%

    No Known Activations