© 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. 29750
    Prev
    Next
    INDEX
    Explanations

    planned parenthood

    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
    åĩ¹
    -0.11
    æĻ¯å¾·
    -0.10
     bak
    -0.09
    ä¸ĢåĪ»
    -0.08
    urus
    -0.08
    ç¼Ł
    -0.08
    è¯Ģ
    -0.08
    ides
    -0.08
     bum
    -0.08
    _ru
    -0.08
    POSITIVE LOGITS
    èĢħ
    0.09
    æĺİ天
    0.09
    ìļ´ëıĻ
    0.08
    æķĽ
    0.08
    åºĸ
    0.08
     пÑĥÑĤ
    0.08
    èIJ¥
    0.08
    vect
    0.08
    主ä½ĵ
    0.08
    atted
    0.08
    Activations Density 0.003%

    No Known Activations