© 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. 880
    Prev
    Next
    INDEX
    Explanations

    Olympic events and competitions

    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
    å¸ĤæķĻèĤ²å±Ģ
    -0.10
     ÑĢеб
    -0.09
     hatch
    -0.09
    xCA
    -0.09
    ç´łåħ»
    -0.09
    åĶ
    -0.09
    æħ¢æħ¢åľ°
    -0.09
    çľģåĨħ
    -0.08
    ç»ĻåŃ©åŃIJ
    -0.08
    ä½ĵè´´
    -0.08
    POSITIVE LOGITS
    æ¿Ģ
    0.11
    åIJĦåĽ½
    0.09
    æµ·å¤ĸ
    0.09
     boyc
    0.09
    ABCDEFG
    0.09
    åĩºéģĵ
    0.09
    å¤§åĽ½
    0.08
     ожи
    0.08
    еÑĤÑĮ
    0.08
    åĽŀåĽ½
    0.08
    Activations Density 0.185%

    No Known Activations