© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    "job", "kingdom", "children", "world", "people"

    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
    çļĦåIJĦç§į
    -0.08
    èįı
    -0.08
    满满
    -0.08
    åľ¨é¦Ļ港
    -0.08
    笫
    -0.08
    åIJĪä¸Ģ
    -0.08
    深度
    -0.08
    ä¸ĵä¸ļ人士
    -0.08
    çĮ¬
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.10
    ä¹Łå°±æĺ¯è¯´
    0.10
    алÑĮн
    0.08
     thiên
    0.08
    èĢĮä¸įæĺ¯
    0.08
    è¿Ļä¹Łæĺ¯
    0.08
    åŃĹæł·
    0.08
    è¿Ļæĺ¯
    0.08
    uck
    0.08
    IELDS
    0.08
    Activations Density 0.320%

    No Known Activations