© 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. 26812
    Prev
    Next
    INDEX
    Explanations

    privacy and data protection

    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
    åĬ±
    -0.10
    ä¸Ģ件äºĭ
    -0.10
    åįıä¼ļä¼ļåijĺ
    -0.10
    认
    -0.10
    被害
    -0.10
    éĢĥèĦ±
    -0.09
    讲究
    -0.09
    iT
    -0.09
    å©Ĩ
    -0.09
    代çIJĨåķĨ
    -0.09
    POSITIVE LOGITS
    迳
    0.09
    交å¾Ģ
    0.08
     privat
    0.08
     Hue
    0.08
    åĮ¿åIJį
    0.08
    åĴĮæľįåĬ¡
    0.08
     anonymously
    0.08
    aro
    0.08
     Accuracy
    0.08
    isser
    0.08
    Activations Density 0.136%

    No Known Activations