© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2790
    Prev
    Next
    INDEX
    Explanations

    women and gender roles

    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
    æĸ°æĺ¥
    -0.07
    人åĵģ
    -0.07
    illac
    -0.07
    ikon
    -0.07
    éŃĤéŃĦ
    -0.06
    ullo
    -0.06
    olit
    -0.06
    èł
    -0.06
    åŃ½
    -0.06
    é»İæĺİ
    -0.06
    POSITIVE LOGITS
    çĶ·æĢ§
    0.15
    女æĢ§
    0.15
    女æĢ§åľ¨
    0.15
     women
    0.14
    女æĢ§çļĦ
    0.14
     female
    0.14
    æĢ§åĪ«
    0.14
     gender
    0.13
    çĶ·æĢ§çļĦ
    0.13
     male
    0.13
    Activations Density 0.223%

    No Known Activations