© 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. 47610
    Prev
    Next
    INDEX
    Explanations

    add to calendar

    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
     Pet
    -0.09
    amer
    -0.09
    æģ¢å¤įæŃ£å¸¸
    -0.09
    æµģä¼ł
    -0.09
    ç½²
    -0.09
    æµģè¡Į
    -0.09
    amel
    -0.09
    æģ¢
    -0.08
    rog
    -0.08
    ugo
    -0.08
    POSITIVE LOGITS
    ç»Ŀ对æĺ¯
    0.10
    æģį
    0.10
    åħ³æ³¨
    0.09
    éĩįçĤ¹åħ³æ³¨
    0.09
    CED
    0.09
    æĪ´ä¸Ĭ
    0.09
     Äijức
    0.09
    èĤ¯å®ļæĺ¯
    0.09
    å¼Ģ车
    0.09
    è¿ĻæĿ¡
    0.08
    Activations Density 0.025%

    No Known Activations