© 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. 64390
    Prev
    Next
    INDEX
    Explanations

    spouse or partner

    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
    è¿ĻåŃ©åŃIJ
    -0.09
    å°ijå¹´
    -0.09
    å°ijå¹´çļĦ
    -0.08
    常客
    -0.08
    çļĦå°ijå¹´
    -0.08
     Miner
    -0.08
     Adolesc
    -0.07
    伯伯
    -0.07
    ssen
    -0.07
    人ä¸İ人ä¹ĭéĹ´
    -0.07
    POSITIVE LOGITS
    /part
    0.11
     spouses
    0.10
    妻åŃIJ
    0.10
    妻
    0.10
    -wife
    0.09
    éħįåģ¶
    0.09
     Wife
    0.09
     partners
    0.09
     wife
    0.09
     spouse
    0.09
    Activations Density 0.177%

    No Known Activations