© 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. 47740
    Prev
    Next
    INDEX
    Explanations

    try experiment search tuning

    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
    æķħ乡
    -0.10
    å¾Ĺ天çĭ¬åİļ
    -0.10
    ãģĿãģ®ãģ¾ãģ¾
    -0.09
     ìĸ´ëĸ
    -0.09
    æķ£åıij
    -0.09
    大巴
    -0.08
    åĩ¹
    -0.08
    Ana
    -0.08
    æĢĿç»´æĸ¹å¼ı
    -0.08
    åĪĿå¿ĥ
    -0.08
    POSITIVE LOGITS
     trial
    0.16
    è¯ķéªĮ
    0.16
    æij¸ç´¢
    0.15
    å°Ŀè¯ķ
    0.14
    è¯ķ
    0.13
    試
    0.13
    æݢ索
    0.13
    缴åĪ°
    0.12
    trial
    0.12
    è¯ķéªĮåĮº
    0.12
    Activations Density 0.146%

    No Known Activations