© 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. 52427
    Prev
    Next
    INDEX
    Explanations

    the latest

    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
    .cgi
    -0.08
    å¸ĮæľĽå¤§å®¶
    -0.08
    ute
    -0.08
    pte
    -0.08
    书记
    -0.08
    ordinate
    -0.08
    æĪijçĽ¸ä¿¡
    -0.08
    steady
    -0.08
    éĿ
    -0.08
    pects
    -0.08
    POSITIVE LOGITS
    PREC
    0.09
    ìŀ¡
    0.09
    ä¸įèĪį
    0.08
    åĨħå¹ķ
    0.08
     <![
    0.08
    éĺĹ
    0.08
    unix
    0.08
    æľĪä¸ĭ
    0.08
    é¢ĨåĨĽ
    0.08
    ç²¾å¯Ĩ
    0.08
    Activations Density 0.075%

    No Known Activations