© 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. 18582
    Prev
    Next
    INDEX
    Explanations

    gay and homosexual identity

    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
    æ¬ł
    -0.08
    éļĻ
    -0.07
    æļĩ
    -0.06
    åĬŁèĩ£
    -0.06
    TEX
    -0.06
    tring
    -0.06
     creditors
    -0.06
    kov
    -0.06
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.06
    缺
    -0.06
    POSITIVE LOGITS
    åIJĮæĢ§æģĭ
    0.12
     LGBTQ
    0.11
     LGBT
    0.10
     gay
    0.10
     transgender
    0.10
     bisexual
    0.10
     lesbian
    0.10
    gay
    0.10
    -gay
    0.09
     homosexuality
    0.09
    Activations Density 0.155%

    No Known Activations