© 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. 55421
    Prev
    Next
    INDEX
    Explanations

    by or of followed by proper noun

    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
    æ°IJ
    -0.09
    orns
    -0.09
    ç»Ļ她
    -0.08
    onas
    -0.08
    idas
    -0.08
    ç²¼
    -0.08
    æ°ijä¼ģ
    -0.08
     Wyatt
    -0.08
     Irma
    -0.08
    åĢĴéĹŃ
    -0.08
    POSITIVE LOGITS
    æĺ¯è°ģ
    0.12
    å§ļæĺİ
    0.10
    飩
    0.10
    æŶ任
    0.10
    ä¸Ģ个人
    0.10
    骧
    0.10
    æĪijåĴĮ
    0.10
    ä¹³
    0.10
    诸å¦Ĥ
    0.09
     اÙĦجÙĨ
    0.09
    Activations Density 0.406%

    No Known Activations