© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4609
    Prev
    Next
    INDEX
    Explanations

    transgender and gender issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭ¾
    -0.10
    ර
    -0.10
    ennon
    -0.09
    çľ¾
    -0.09
     harmless
    -0.09
    媾
    -0.09
    åįķ身
    -0.09
    èĤ©èĨĢ
    -0.09
    ulty
    -0.09
    éļıæīĭ
    -0.09
    POSITIVE LOGITS
    æĢ§åĪ«
    0.12
    gender
    0.10
     gender
    0.10
    Gender
    0.10
     Gender
    0.10
    æ®ĸ
    0.09
    çħ§
    0.09
    æķ´å½¢
    0.08
    人éĢł
    0.08
     birth
    0.08
    Activations Density 0.094%

    No Known Activations