© 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. 49298
    Prev
    Next
    INDEX
    Explanations

    magical, miracle, fulfillment, or starving

    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
     khá
    -0.11
    æĺİçĻ½äºĨ
    -0.10
    ä¹Łç®Ĺ
    -0.10
    没äºĨ
    -0.10
    quared
    -0.10
     escal
    -0.09
    ptest
    -0.09
    离å¼ĢäºĨ
    -0.09
    ivers
    -0.08
    itch
    -0.08
    POSITIVE LOGITS
    ç«ĭ马
    0.11
    æľīå¤ļä¹Ī
    0.10
    å¤ļä¹Ī
    0.10
    ordes
    0.09
    eti
    0.09
    åĥı
    0.09
    大éĿ¢ç§¯
    0.09
    à¹ģà¸Ī
    0.09
    æŁIJ
    0.09
    大äºĭ
    0.09
    Activations Density 0.116%

    No Known Activations