© 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. 5072
    Prev
    Next
    INDEX
    Explanations

    articles for use

    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
     Ansi
    -0.09
    åīįä¸ĸ
    -0.09
    足迹
    -0.09
    貧
    -0.09
    æĦŁåı¹
    -0.08
    rä
    -0.08
    eni
    -0.08
    çĨĬ
    -0.08
    ä¹³
    -0.08
    误
    -0.08
    POSITIVE LOGITS
    åį³å°ĨåĪ°æĿ¥
    0.10
    åħħå®ŀ
    0.10
    æĺİçĻ½
    0.09
    æĬ¥çº¸
    0.09
     ÐŁÐ¾Ñĩем
    0.09
    สรร
    0.09
    è¿Ļ个ä¸ĸçķĮ
    0.09
    ä¾Ľ
    0.09
    Canon
    0.09
    ëģĶ
    0.08
    Activations Density 0.077%

    No Known Activations