© 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. 46915
    Prev
    Next
    INDEX
    Explanations

    mating and marriage choices

    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
    人çļĦçĶŁåij½
    -0.09
    人åij½
    -0.07
    ductor
    -0.07
    йда
    -0.07
    leon
    -0.07
    åľ¨è¡ĮåĬ¨
    -0.07
    ائÙĨ
    -0.07
    åį§
    -0.07
     Äijá»±ng
    -0.07
    inerary
    -0.07
    POSITIVE LOGITS
     assort
    0.10
     incest
    0.09
    éļıæľº
    0.09
    èĩªè§ī
    0.09
    ä¹łæĢ§
    0.08
     preferences
    0.08
    æĦıæĦ¿
    0.08
    èĩªè§īæĢ§
    0.08
     RANDOM
    0.08
    olin
    0.07
    Activations Density 0.015%

    No Known Activations