© 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. 18019
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.08
    ä½ĨæĦ¿
    -0.07
    æ²³éķĩ
    -0.07
    /yyyy
    -0.07
     indef
    -0.06
    éļĪ
    -0.06
    IDER
    -0.06
     acond
    -0.06
    ruzzo
    -0.06
    å¾Ĺ人
    -0.06
    POSITIVE LOGITS
    otch
    0.07
    æѤæŶ
    0.07
    uros
    0.07
    æľīè¯Ŀ
    0.07
    åIJīæĸ¯
    0.07
    unker
    0.07
    еÑĢе
    0.07
    å°±ä¸įæĺ¯
    0.07
    imet
    0.07
    ben
    0.06
    Activations Density 0.009%

    No Known Activations