© 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. 22790
    Prev
    Next
    INDEX
    Explanations

    ography deposition etry ization

    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
    们çļĦ
    -0.10
    们
    -0.10
    ças
    -0.10
     ÑĢейÑĤинг
    -0.09
    /tools
    -0.09
    lica
    -0.09
    sgi
    -0.09
    hood
    -0.09
    sWith
    -0.09
    åĢij
    -0.09
    POSITIVE LOGITS
    æ³ķ
    0.11
    æĪIJåĬŁçİĩ
    0.11
    è¿Ļç§įæĸ¹å¼ı
    0.10
    è¿ĩç¨ĭä¸Ń
    0.10
    åĻ¨
    0.10
    æĸ¹å¼ı
    0.10
    ë²ķ
    0.10
    -done
    0.09
     done
    0.09
    åıijçĶŁåľ¨
    0.09
    Activations Density 1.045%

    No Known Activations