© 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. 23215
    Prev
    Next
    INDEX
    Explanations

    national economy and society

    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
    缮çļĦåľ¨äºİ
    -0.11
    ä¸Ģç»ı
    -0.10
    éģŃ
    -0.09
    åħ¬å¼Ģåıij
    -0.09
    æĤ¬æĮĤ
    -0.09
    éħ¬
    -0.09
    аÑĩ
    -0.09
    å·²ç»ıæĪIJ为
    -0.09
    åĩºèº«
    -0.09
    è§Ħç«ł
    -0.08
    POSITIVE LOGITS
    lav
    0.09
    æ¥Ķ
    0.09
    æķ´ä½ĵ
    0.09
    沧
    0.09
    念
    0.09
    üss
    0.09
    Smarty
    0.08
    æĢ»ä½ĵ
    0.08
    çİ
    0.08
    åĵī
    0.08
    Activations Density 0.192%

    No Known Activations