© 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. 64042
    Prev
    Next
    INDEX
    Explanations

    perfect vacation, vendor, type, hair, home, solution

    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
    sher
    -0.10
    骢
    -0.10
    轩è¾ķ
    -0.10
    头éĥ¨
    -0.09
    笨
    -0.09
    PEG
    -0.08
     depreci
    -0.08
    ixo
    -0.08
    ä¸Ģä¸ĭåŃIJ
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
    è¯
    0.09
     zwar
    0.09
    _git
    0.08
    æģ¯
    0.08
    æĸ½
    0.08
    çļĦéĢīæĭ©
    0.08
    说å®ŀè¯Ŀ
    0.08
     ding
    0.08
    Activations Density 0.001%

    No Known Activations