© 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. 39324
    Prev
    Next
    INDEX
    Explanations

    sex and gender demographics

    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
    æľªæĪIJ
    -0.09
    olic
    -0.08
     tá»ĩ
    -0.08
    ç¬ĥ
    -0.08
    èµ·æŃ¥
    -0.08
    auss
    -0.08
    è·Ľ
    -0.08
    ones
    -0.08
    cir
    -0.08
    èĪĤ
    -0.08
    POSITIVE LOGITS
    -song
    0.09
    AGES
    0.09
    UAL
    0.09
    male
    0.09
    æIJŃ
    0.08
    etti
    0.08
    éľı
    0.08
     psych
    0.08
    ajor
    0.08
    åĬ¡
    0.08
    Activations Density 0.064%

    No Known Activations