© 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. 47525
    Prev
    Next
    INDEX
    Explanations

    op.org

    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
    èĢĮéĿŀ
    -0.08
    è¯Ŀ说
    -0.08
    IPS
    -0.08
    ä»ĺ
    -0.08
    æ¯ıä¸Ģ天
    -0.08
    åĹĴ
    -0.08
    èĭ»
    -0.08
    裾
    -0.08
    缸åħ³è´Łè´£
    -0.08
    ç®į
    -0.08
    POSITIVE LOGITS
    ä¸į太好
    0.10
    ä¾Ŀ次
    0.08
    åĨ²çªģ
    0.08
    along
    0.08
    gle
    0.08
     Leer
    0.08
    çľĭ好
    0.08
    añ
    0.08
    rawl
    0.08
    otron
    0.08
    Activations Density 0.055%

    No Known Activations