© 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. 4654
    Prev
    Next
    INDEX
    Explanations

    cut down

    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
     qual
    -0.09
    ä¸įä¸Ĭ
    -0.09
    èµĦæł¼
    -0.09
    é«ĺãģı
    -0.08
    ä¸Ī
    -0.08
    æĮ¡ä½ı
    -0.08
    åŁŃ
    -0.08
    изаÑĤоÑĢ
    -0.08
    ä¸įèĪį
    -0.08
     Shore
    -0.08
    POSITIVE LOGITS
    æ´½
    0.09
    æijĩ
    0.08
    çħĮ
    0.08
    ADI
    0.08
    æĹĭ
    0.08
    backs
    0.08
    éģĽ
    0.08
    вÑıз
    0.08
    深深çļĦ
    0.08
    ç«ĭ马
    0.08
    Activations Density 0.018%

    No Known Activations