© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    acronyms with abbreviations

    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
    istingu
    -0.06
     peine
    -0.06
    inator
    -0.06
    ä¸įå®ī
    -0.06
     (()
    -0.06
    ä¸įæĦģ
    -0.06
    “
    -0.05
    ä¸įç»ı
    -0.05
    è¶ħè¿ĩ约
    -0.05
    ten
    -0.05
    POSITIVE LOGITS
    edList
    0.08
    ldb
    0.08
    帼
    0.07
    ä½ľçļĦ
    0.07
    åį¡åĴĮ
    0.07
    azy
    0.07
    æĤ¨çļĦéĹ®é¢ĺ
    0.07
    çĻ¾å¿Ļ
    0.07
    .GetString
    0.07
    dá
    0.07
    Activations Density 0.413%

    No Known Activations