© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    one version

    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
     whichever
    -0.07
     accordingly
    -0.07
     instances
    -0.07
    åIJĦå¼ıåIJĦ
    -0.06
    `;
    -0.06
    _instance
    -0.06
    æĦŁåįģ足
    -0.06
     instance
    -0.06
     whoever
    -0.06
    instance
    -0.06
    POSITIVE LOGITS
    Ùĩب
    0.10
    åĥıä½ł
    0.08
    对ä¸Ģ个
    0.08
    LOB
    0.08
    æĪIJè¿Ļæł·
    0.07
    erdere
    0.07
    æŁIJ
    0.07
    oola
    0.07
    è¿Ļä¹Ī好çļĦ
    0.07
    并åıĸå¾Ĺ
    0.07
    Activations Density 0.095%

    No Known Activations