© 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. 3258
    Prev
    Next
    INDEX
    Explanations

    ASP.NET applications and tools

    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
    æľīæĦı
    -0.10
    è²Ĥ
    -0.09
    ially
    -0.09
    ä¸ĩ象
    -0.09
    åĭ¤
    -0.09
    ç¼¢
    -0.08
    履约
    -0.08
    é¦Ķ
    -0.08
    pad
    -0.08
    avin
    -0.08
    POSITIVE LOGITS
    çľĭä¸Ģä¸ĭ
    0.09
    _timing
    0.08
    ä»ĸ们ä¼ļ
    0.08
    æİ¥çĿĢ
    0.08
    该åİ¿
    0.08
    è¯ķè¯ķ
    0.08
    æĿĪ
    0.08
    ä»ĸä¼ļ
    0.07
     timestep
    0.07
    çľĭçľĭ
    0.07
    Activations Density 0.252%

    No Known Activations