© 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. 11600
    Prev
    Next
    INDEX
    Explanations

    for increasing

    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
    缴è¨Ģ
    -0.10
    éªł
    -0.09
    ä¸ĢæĿ¯
    -0.09
    ä¸įæĸŃçļĦ
    -0.09
    档次
    -0.09
    ä¸Ģè¶Ł
    -0.08
    åįŁ
    -0.08
    é«ĺæīĭ
    -0.08
    lap
    -0.08
    angep
    -0.08
    POSITIVE LOGITS
    墨
    0.09
    Rare
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.09
    è¹ļ
    0.09
    ponder
    0.09
    hte
    0.09
    förder
    0.09
    à¹ĥà¸Ļà¸ģาร
    0.09
    æĽ¾
    0.09
     Rare
    0.08
    Activations Density 0.202%

    No Known Activations