© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21613
    Prev
    Next
    INDEX
    Explanations

    for purpose or context

    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
    被认为
    -0.10
    ä¸įä¸ĭ
    -0.09
    åĤ²
    -0.09
    å¯ĨåĪĩåħ³æ³¨
    -0.09
    asm
    -0.09
    ç»ıæŁ¥
    -0.08
    æĬ±
    -0.08
    RTOS
    -0.08
    åı°åĮĹ
    -0.08
    æĭľ
    -0.08
    POSITIVE LOGITS
    à¸ķาย
    0.09
    æľªæĿ¥
    0.09
    игÑĢа
    0.09
    ãģ¨ãģ¯ãģĦãģĪ
    0.09
     Coch
    0.09
    大æĪĺ
    0.09
    åĬ³ç´¯
    0.09
     sẵn
    0.08
     Wade
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    Activations Density 0.092%

    No Known Activations