© 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. 50570
    Prev
    Next
    INDEX
    Explanations

    Cherokee, Mohawk, Cheyenne, Navajo

    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
    æ¼ķ
    -0.11
    ingly
    -0.10
    arian
    -0.10
    ary
    -0.10
    为æ°ij
    -0.10
    é¾Ħ
    -0.09
    ivity
    -0.08
    -zA
    -0.08
    ÑĢай
    -0.08
    otch
    -0.08
    POSITIVE LOGITS
    è°ļ
    0.09
    odu
    0.08
    yy
    0.08
    樾
    0.08
    æĸ°ä¸ĸ纪
    0.08
     edi
    0.08
    ä¸įå¿ħ
    0.08
    Chief
    0.08
    -owned
    0.08
     sca
    0.08
    Activations Density 0.012%

    No Known Activations