© 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. 24176
    Prev
    Next
    INDEX
    Explanations

    possessive followed by proper noun or publication

    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
    creation
    -0.09
    5
    -0.09
    为主é¢ĺçļĦ
    -0.09
    4
    -0.09
    6
    -0.09
    9
    -0.09
    Creation
    -0.09
    0
    -0.09
    æķĻä¼ļ
    -0.09
    7
    -0.09
    POSITIVE LOGITS
    åĭ¾
    0.10
    entially
    0.09
    æĽĻ
    0.09
     khảo
    0.09
    æĹłåı¯
    0.09
    åħ³äºİ
    0.09
    uber
    0.09
    çĪ±åĽ½ä¸»ä¹ī
    0.09
    uting
    0.09
    /proto
    0.09
    Activations Density 0.028%

    No Known Activations