© 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. 42926
    Prev
    Next
    INDEX
    Explanations

    file paths starting with /Users or C:\Users

    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
    .weixin
    -0.07
    Jud
    -0.07
    çī¹æĸ¯
    -0.06
    认è¯ģåķĨ家
    -0.06
    _inds
    -0.06
    çļĦæķ´ä½ĵ
    -0.06
    æ¸ħç®Ĺä¿¡æģ¯
    -0.06
    "https
    -0.06
    ä»ĸ家
    -0.06
    -fetch
    -0.06
    POSITIVE LOGITS
    æµĭè¯ķ
    0.08
     pilote
    0.08
     pilot
    0.08
     testing
    0.08
    è¯ķéªĮ
    0.08
     test
    0.08
    -testing
    0.07
    Projects
    0.07
    raje
    0.07
    å®ŀéªĮ
    0.07
    Activations Density 0.448%

    No Known Activations