© 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. 32120
    Prev
    Next
    INDEX
    Explanations

    wholesale business and pricing

    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
    æŀģ端
    -0.10
    ä¼ĺåĮĸ
    -0.09
    对ç«ĭ
    -0.09
    款
    -0.09
    Extreme
    -0.08
    åı¥
    -0.08
    ãģĽãģĦ
    -0.08
    èķ´
    -0.08
    éĢĨåĬ¿
    -0.08
    رÙĪÙħ
    -0.08
    POSITIVE LOGITS
    æī¹åıij
    0.12
    祺
    0.09
    大åݦ
    0.09
    icket
    0.09
    ä¸ĢèĤ¡
    0.09
    åıĸå¾ĹäºĨ
    0.08
    è´±
    0.08
    ä»·
    0.08
    åħ¼
    0.08
    å¦Ĥå®ŀ
    0.08
    Activations Density 0.038%

    No Known Activations