© 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. 35697
    Prev
    Next
    INDEX
    Explanations

    of possessive/determiner pairings

    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
    æķ²
    -0.10
     вообÑīе
    -0.10
    äºĪ
    -0.09
    oller
    -0.09
    èĦļæŃ¥
    -0.09
    èį·
    -0.08
    å±ģèĤ¡
    -0.08
    able
    -0.08
    ä»İä¸Ń
    -0.08
    å¼Ģåıij建设
    -0.08
    POSITIVE LOGITS
    çĽĬ
    0.09
    utes
    0.09
    建ç«ĭèµ·
    0.09
    phones
    0.09
    ailles
    0.09
    å·²ç»ıæľī
    0.09
    èĢĮåĩº
    0.08
    _ALREADY
    0.08
    åIJĪæ³ķ
    0.08
    离
    0.08
    Activations Density 0.159%

    No Known Activations