© 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. 7960
    Prev
    Next
    INDEX
    Explanations

    names and surnames

    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
    енд
    -0.09
    涤
    -0.09
    æĮĿ
    -0.09
    aidu
    -0.09
    epam
    -0.09
    elor
    -0.09
    æģķ
    -0.09
    _TI
    -0.09
    adin
    -0.09
    è¿ŁåĪ°
    -0.09
    POSITIVE LOGITS
     pers
    0.08
    åįĥå¹´
    0.07
    è¿Ļåı¥è¯Ŀ
    0.07
     RESOURCE
    0.07
     kr
    0.07
    иÑĤелÑĮно
    0.07
    idea
    0.07
     Dayton
    0.07
    çĽĪ
    0.07
    OrCreate
    0.07
    Activations Density 0.197%

    No Known Activations