© 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. 12072
    Prev
    Next
    INDEX
    Explanations

    those or people

    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
    Not in Any Lists

    No Comments

    Negative Logits
    人们çļĦ
    -0.09
    åѦçĶŁçļĦ
    -0.08
    å¤ĩ
    -0.08
    åħ¬åı¸çļĦ
    -0.08
    åIJ¬å®Į
    -0.08
    人åĿĩ
    -0.08
    éĥ½æ²¡
    -0.08
    æĪ¾
    -0.08
    è¡¡
    -0.08
    apl
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.20
     those
    0.17
     ones
    0.17
    those
    0.16
     Those
    0.15
    Those
    0.14
     Ones
    0.13
    ones
    0.12
    éĤ£åĢĭ
    0.11
     ceux
    0.11
    Activations Density 0.086%

    No Known Activations