© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29576
    Prev
    Next
    INDEX
    Explanations

    spoken names ending

    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
    Negative Logits
    InstanceOf
    -0.09
     ghé
    -0.08
    ä¸ĵ人
    -0.08
    ãĤīãģı
    -0.08
    ç¼Ĩ
    -0.08
    é¹Ĺ
    -0.08
    æħij
    -0.08
    åĮºæĶ¿åºľ
    -0.08
    ugi
    -0.08
    åĤ¬çĶŁ
    -0.08
    POSITIVE LOGITS
    妻åŃIJ
    0.10
    innen
    0.09
    èµ°ä¸Ĭ
    0.09
    ä¸Ģè¾¹
    0.09
    -même
    0.09
    æīĢåľ¨çļĦ
    0.09
    身ä½ĵ
    0.09
    ש×Ŀ
    0.09
    oppers
    0.09
    ä¸ĢéĿ¢
    0.08
    Activations Density 0.076%

    No Known Activations