© 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. 35561
    Prev
    Next
    INDEX
    Explanations

    Leonardo Da Vinci or DiCaprio

    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
    纪念ç¢ij
    -0.10
    æ°ijæĹıæĸĩåĮĸ
    -0.10
     ì§ģ
    -0.09
    à¸ģา
    -0.09
    大éģĵ
    -0.09
    ç«ĻçĿĢ
    -0.09
    çģ¯ç¬¼
    -0.09
    幸è¿IJ
    -0.09
     tal
    -0.09
    大夫
    -0.09
    POSITIVE LOGITS
     Leonardo
    0.13
    fas
    0.08
    Nib
    0.08
    pine
    0.08
    igma
    0.08
    zas
    0.08
    æĥľ
    0.08
    çł´è§£
    0.08
    -arrow
    0.08
    æĹģ
    0.08
    Activations Density 0.056%

    No Known Activations