© 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. 16814
    Prev
    Next
    INDEX
    Explanations

    easy to

    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
    ä¹ĭå¤ľ
    -0.11
    æĢ¥éľĢ
    -0.10
    æĽ¾ä»»
    -0.10
    åı¯æĥľ
    -0.10
    pers
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    åĪ°åºķæĺ¯
    -0.09
    åı¯èĥ½æĢ§
    -0.09
    åīįä»»
    -0.09
    æľĢåIJĪéĢĤ
    -0.09
    POSITIVE LOGITS
     dÃłng
    0.09
     Easily
    0.09
    æİ©çĽĸ
    0.09
    å¾Ī容æĺĵ
    0.09
    å°±æĬĬ
    0.08
     easily
    0.08
    æĦŁåıĹåĪ°
    0.08
    OfType
    0.08
     easy
    0.08
    失
    0.08
    Activations Density 0.027%

    No Known Activations