© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    comedians and shows

    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
     dur
    -0.09
    law
    -0.09
    ç¬ı
    -0.08
    amide
    -0.08
    俱ä¹IJ
    -0.08
    lah
    -0.08
     Ballet
    -0.08
    åľ°ä¸Ń
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.08
    lag
    -0.08
    POSITIVE LOGITS
    swith
    0.09
    ä¸įæĥ³
    0.09
    主æĮģ人
    0.08
    忽
    0.08
    .foreach
    0.08
    TÄ°
    0.08
    奥巴马
    0.08
    ertino
    0.08
    ÑĢÑĭв
    0.08
    å®īä¸ľå°¼
    0.08
    Activations Density 0.003%

    No Known Activations