© 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. 16546
    Prev
    Next
    INDEX
    Explanations

    amount of quantity or time

    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
    éļıæŶ
    -0.11
    éļ¨æĻĤ
    -0.09
    æ³±
    -0.09
    误ä¼ļ
    -0.08
    TIM
    -0.08
    esture
    -0.08
    ield
    -0.08
    plemented
    -0.08
    éĢĤæŶ
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    POSITIVE LOGITS
    å¿ĥè¡Ģ
    0.11
    å¹´éĻIJ
    0.10
    à¹Ģà¸Ļ
    0.09
    èķĬ
    0.09
    æį§
    0.09
    çļĦåĬĽéĩı
    0.09
    umer
    0.09
     thác
    0.09
    è¿İæĿ¥äºĨ
    0.08
    >Lorem
    0.08
    Activations Density 0.036%

    No Known Activations