© 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. 10157
    Prev
    Next
    INDEX
    Explanations

    best serve, predict, create, 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
    大æĪ·
    -0.09
    ä¿Ĺè¯Ŀ说
    -0.09
    çīĩåŃIJ
    -0.08
    æ¯Ĵç´ł
    -0.08
    è¿ĽèĢĮ
    -0.08
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
    å¤ļå¹´çļĦ
    -0.08
     gerne
    -0.08
    ä¹ĭ乡
    -0.08
    ited
    -0.08
    POSITIVE LOGITS
     Pru
    0.09
    some
    0.09
    祺
    0.09
    æĸ½å±ķ
    0.09
    .motion
    0.09
    æ¨¡æł·
    0.09
    ucci
    0.09
    æĺ¯éĿŀ
    0.08
    åıįæĺł
    0.08
    éĻį
    0.08
    Activations Density 0.016%

    No Known Activations