© 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. 12176
    Prev
    Next
    INDEX
    Explanations

    personally identifiable information

    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
    ç±į
    -0.11
    éģį
    -0.09
    满èĦ¸
    -0.09
    äºīåıĸ
    -0.09
    éĻį
    -0.09
    åIJĮè¡Į
    -0.08
    ovah
    -0.08
    å¹½é»ĺ
    -0.08
    dess
    -0.08
    éĢļ讯
    -0.08
    POSITIVE LOGITS
    éķĿ
    0.09
    vl
    0.09
    åĢĭ人
    0.09
    Bush
    0.09
    æ¯ıåij¨
    0.09
    rell
    0.09
    å®Ŀè´Ŀ
    0.09
    æ±ľ
    0.09
    óst
    0.08
    оÑĩка
    0.08
    Activations Density 0.003%

    No Known Activations