© 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. 26215
    Prev
    Next
    INDEX
    Explanations

    among

    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
     Markets
    -0.10
    acker
    -0.09
    omens
    -0.09
     gì
    -0.09
    ró
    -0.09
     Bis
    -0.09
    olon
    -0.09
    alking
    -0.09
    é©Ń
    -0.09
    ãģĬãģĿãĤīãģı
    -0.09
    POSITIVE LOGITS
     ÑģебÑı
    0.13
    -sama
    0.11
    ãģĹãģ¾ãģĦ
    0.11
    ãģĹãģ¾ãģĨ
    0.10
    /about
    0.10
    /on
    0.09
     ниÑħ
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
    å¹´æĿ¥
    0.09
    est
    0.09
    Activations Density 0.032%

    No Known Activations