© 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. 22890
    Prev
    Next
    INDEX
    Explanations

    numbers after biblical citations

    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
    itz
    -0.09
    çĽĬ
    -0.09
    缸åIJĮçļĦ
    -0.08
    éĻµ
    -0.08
    ç½ij讯
    -0.08
    onic
    -0.08
    æľ¬äºº
    -0.08
    æĸ°ä¸ĸ纪
    -0.07
    anks
    -0.07
    WS
    -0.07
    POSITIVE LOGITS
    å¼ĢèįĴ
    0.09
    åįĩ级æĶ¹éĢł
    0.09
    ä¸ĭéĿ¢æĺ¯å°ı
    0.09
     trá»Ŀi
    0.08
    ÑĨов
    0.08
    _Custom
    0.08
    åĪĽæĸ°é©±åĬ¨
    0.08
    æľĢç¾İ
    0.08
    .rf
    0.08
    اء
    0.08
    Activations Density 0.048%

    No Known Activations