© 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. 64088
    Prev
    Next
    INDEX
    Explanations

    as soon as

    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
    ä¸ī项
    -0.09
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    æł¹æľ¬å°±ä¸į
    -0.08
    æį¢åıĸ
    -0.08
    ä¼IJ
    -0.08
    âľį
    -0.08
    ä»Ģä¹Īæł·çļĦ
    -0.08
    oded
    -0.08
    åİĨ
    -0.08
    åĽłä¸ºæĪij们
    -0.08
    POSITIVE LOGITS
    olin
    0.09
    OrElse
    0.09
    (er
    0.09
    æļ¨
    0.09
    ä¼´
    0.09
    izzes
    0.08
    让人们
    0.08
    bye
    0.08
    _timing
    0.08
    çģµ
    0.08
    Activations Density 0.016%

    No Known Activations