© 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. 26133
    Prev
    Next
    INDEX
    Explanations

    food components and land areas

    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
    丰
    -0.09
    æīįçŁ¥éģĵ
    -0.09
    s
    -0.08
     Consolid
    -0.08
    رÙĩ
    -0.08
     лидеÑĢ
    -0.08
    é»ĺ
    -0.07
    iating
    -0.07
    mith
    -0.07
    æĻ®åıĬ
    -0.07
    POSITIVE LOGITS
    éĻ©
    0.10
    éļª
    0.09
    两项
    0.09
    sek
    0.09
    اÙĨÙĬØ©
    0.09
    åĹŁ
    0.09
    æīĢæıIJä¾Ľ
    0.09
    zan
    0.08
    _PRI
    0.08
    usat
    0.08
    Activations Density 0.011%

    No Known Activations