© 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. 30550
    Prev
    Next
    INDEX
    Explanations

    immigrant and foreign names

    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
    ä¸ĭ乡
    -0.10
    çĮª
    -0.10
    ายà¸Ļ
    -0.09
     Southwest
    -0.08
    åijĹ
    -0.08
    изм
    -0.08
    æĪ¡
    -0.08
    vae
    -0.08
    ç®´
    -0.08
    寨
    -0.08
    POSITIVE LOGITS
    åĽŀåĽ½
    0.10
    AKE
    0.10
    çķĻåѦçĶŁ
    0.10
    æ²īé»ĺ
    0.09
    å¥Ķ
    0.09
    ç¼ij
    0.09
    loff
    0.09
    åľ¨ç¾İåĽ½
    0.09
     immigrant
    0.08
    è£ĺ
    0.08
    Activations Density 0.250%

    No Known Activations