© 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. 11281
    Prev
    Next
    INDEX
    Explanations

    divorce proceedings

    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
    ocache
    -0.08
    åĮ
    -0.07
    åľŁåľ°æĬµæĬ¼
    -0.07
    adr
    -0.07
    è³ŀ
    -0.07
    mouseover
    -0.07
    æĭħä¿Ŀé£İéĻ©
    -0.07
    被ç½ļ
    -0.07
     thirsty
    -0.07
    åIJijåѦçĶŁ
    -0.06
    POSITIVE LOGITS
    åĪĨå±ħ
    0.13
     divorce
    0.12
    离å©ļ
    0.12
     separation
    0.11
     divor
    0.10
     marital
    0.10
     matrimon
    0.10
     breakup
    0.10
    æ°ijæĶ¿å±Ģ
    0.09
     ÑĢазвод
    0.09
    Activations Density 0.099%

    No Known Activations