© 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. 59389
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
    滩
    -0.09
    åĨ³æĪĺ
    -0.09
    æĺ¯ä¸Ģ件
    -0.09
    说å®Į
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    çģĮ
    -0.09
    ç³Ł
    -0.09
    ç®į
    -0.09
    .err
    -0.09
    æĮ½
    -0.09
    POSITIVE LOGITS
    æĪijåıijçİ°
    0.09
    ä¸Ģ个
    0.08
    好çļĦ
    0.08
    nÃŃ
    0.08
    æ³¥
    0.08
    ä¸īçĤ¹
    0.07
    ativa
    0.07
    头æĿ¡
    0.07
     lovely
    0.07
    æľ¬æĿ¥
    0.07
    Activations Density 0.071%

    No Known Activations