© 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. 59217
    Prev
    Next
    INDEX
    Explanations

    aims, goals, tasks

    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
    jam
    -0.08
    é¾ĻéŨ
    -0.08
    éļ¾å¿ĺ
    -0.08
    (ht
    -0.08
    åı¤ä»£
    -0.08
    .paths
    -0.08
    æ¡IJ
    -0.08
    人æµģ
    -0.08
    çŁ³å®¶
    -0.08
    èĩªæĿ¥
    -0.08
    POSITIVE LOGITS
    缮çļĦæĺ¯
    0.16
    çļĦä»»åĬ¡
    0.16
    èģĮè´£
    0.15
    æĹ¨åľ¨
    0.14
     aim
    0.14
    ä»»åĬ¡
    0.13
     goal
    0.13
    使åij½
    0.13
     обÑıзан
    0.12
     task
    0.12
    Activations Density 0.091%

    No Known Activations