© 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. 49851
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

    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
    æű
    -0.11
    äºĶè¡Į
    -0.11
    åĩºåľŁ
    -0.09
    ä¸įä½ı
    -0.09
    ä¸įå°½
    -0.09
    ä¸įä¸ĭ
    -0.09
    è°ł
    -0.09
    arded
    -0.09
    ä¸įå®Į
    -0.09
    StyleSheet
    -0.09
    POSITIVE LOGITS
    ä¾ı
    0.11
    èµĦéĩij
    0.09
    ÑģÑĥд
    0.09
    çŃ¹çłģ
    0.09
    æ±ľ
    0.09
     дÑĢÑĥзÑĮÑı
    0.08
    æĤ¬
    0.08
    åī©ä¸ĭ
    0.08
    马æĭīæĿ¾
    0.08
    aint
    0.08
    Activations Density 0.058%

    No Known Activations