© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20491
    Prev
    Next
    INDEX
    Explanations

    tax era

    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
     Duis
    -0.09
     Blond
    -0.08
    vol
    -0.08
    ucas
    -0.08
    å¨
    -0.08
    å¼ķæĵİ
    -0.08
    åŃĸ
    -0.08
    迤
    -0.08
    é§IJ
    -0.08
    isky
    -0.08
    POSITIVE LOGITS
    æݧ
    0.09
     ÑĦиÑĢ
    0.09
    鸱
    0.09
    éĶ»
    0.09
    mast
    0.08
    产ä¸ļåįĩ级
    0.08
    è§īéĨĴ
    0.08
    å½ĺ
    0.08
    æĢĿç´¢
    0.08
    quip
    0.08
    Activations Density 0.302%

    No Known Activations