© 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. 1353
    Prev
    Next
    INDEX
    Explanations

    get together or married

    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
    ä½IJ
    -0.10
    ninger
    -0.09
    exe
    -0.09
    à¹Ģย
    -0.09
    lis
    -0.09
    ä¸ĢäºĮ
    -0.09
    空
    -0.08
    essim
    -0.08
    溢
    -0.08
     blanket
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.10
     rid
    0.10
    çļĦ好
    0.10
    SSIP
    0.09
    elize
    0.09
    ç¥Ľ
    0.09
    翻身
    0.09
    ãģłãģĹ
    0.09
    èĥ³
    0.08
    CodeGen
    0.08
    Activations Density 0.074%

    No Known Activations