© 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. 22108
    Prev
    Next
    INDEX
    Explanations

    published by

    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
    æĨ§
    -0.09
    头顶
    -0.08
    çĴĭ
    -0.08
    ведение
    -0.08
    5
    -0.08
    ï¿£
    -0.08
    zh
    -0.08
    3
    -0.08
    ä¿Ĺ称
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    ä¸įä¹ı
    0.10
    å¾ģéĽĨ
    0.09
    éĽĨåIJĪ
    0.09
    åłĨ积
    0.09
    èĵĸ
    0.09
     collection
    0.08
    ä¿ĿæĮģ
    0.08
    à¹īาà¸ĩ
    0.08
    漪
    0.08
    еÑģÑĤво
    0.08
    Activations Density 0.003%

    No Known Activations