© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37311
    Prev
    Next
    INDEX
    Explanations

    system, chip, device, standard, universal

    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
    ç¡®
    -0.09
    inki
    -0.09
    .nasa
    -0.09
    åĮ»åѦéĻ¢
    -0.09
    轨
    -0.08
    å²Ĺ
    -0.08
    á»Į
    -0.08
     surre
    -0.08
    shal
    -0.08
    olf
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥æ¨¡å¼ı
    0.08
    äºĨè§£ä¸Ģä¸ĭ
    0.08
    stands
    0.08
     stands
    0.08
    å°Ĩè¿İæĿ¥
    0.08
    ir
    0.08
    åĨľä¸ļåĨľæĿij
    0.08
    обоÑĢ
    0.08
    æķĪèĥ½
    0.08
    ible
    0.08
    Activations Density 0.190%

    No Known Activations