© 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. 47563
    Prev
    Next
    INDEX
    Explanations

    sports standings or teams

    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
    æ´ĭ
    -0.10
    _uid
    -0.09
    åİĺ
    -0.09
    寻
    -0.09
    .border
    -0.08
    澤
    -0.08
     зÑĢ
    -0.08
    诣
    -0.08
    ometer
    -0.08
    çªģåĩº
    -0.08
    POSITIVE LOGITS
    缺åı£
    0.10
    ipt
    0.10
    æ¯ıä¸Ģ天
    0.10
    èħŃ
    0.10
    çĶµä¿¡
    0.09
    otes
    0.09
    å½ĵä¹ĭæĹłæĦ§
    0.09
    丰æĶ¶
    0.09
    pcs
    0.09
    OTES
    0.09
    Activations Density 0.103%

    No Known Activations