© 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. 54219
    Prev
    Next
    INDEX
    Explanations

    sex differences and behavior

    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
    æİĸ
    -0.10
    åĽłä¸ºä»ĸ们
    -0.09
     Eugene
    -0.09
    .Quad
    -0.09
     Lod
    -0.09
    olk
    -0.08
    梳
    -0.08
    ä¼Ł
    -0.08
    æ®ĭçĸ¾
    -0.08
    éļĨ
    -0.08
    POSITIVE LOGITS
    åĩij
    0.10
    åħ«åŃĹ
    0.10
    é¥
    0.09
    æł¹åºķ
    0.09
     Exped
    0.09
    å¾Ģå¤ĸ
    0.09
    auction
    0.09
     ÑĤож
    0.09
    åħ»èĤ²
    0.09
    涣
    0.08
    Activations Density 0.119%

    No Known Activations