© 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. 952
    Prev
    Next
    INDEX
    Explanations

    questions starting with "is this"

    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
    æľ¬ç½ijç«Ļ
    -0.12
    åĩ¡æľ¬ç½ij
    -0.11
    è¿Ļç§įæĸ¹å¼ı
    -0.11
    åľ¨æĪijçľĭæĿ¥
    -0.10
     полÑĮзÑĥ
    -0.10
    å¾Īåĸľæ¬¢
    -0.10
    æ·Ģ
    -0.10
    椿
    -0.10
    è¿ĻæĿ¡è·¯
    -0.09
    综åIJĪæĢ§
    -0.09
    POSITIVE LOGITS
     lean
    0.09
     part
    0.08
    å¿ħè¦ģ
    0.08
    æĺ¯
    0.08
    æĦıåij³çĿĢ
    0.08
    æĪIJ为
    0.08
    Ø·ÙĪر
    0.08
     necess
    0.08
     vou
    0.08
    otton
    0.08
    Activations Density 0.022%

    No Known Activations