© 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. 63826
    Prev
    Next
    INDEX
    Explanations

    will or 'll followed by a verb

    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
    è¡Ķæİ¥
    -0.08
    天ä¸ĭ
    -0.08
    èĢĹ
    -0.08
    è¿İæİ¥
    -0.08
    åģļ好
    -0.08
     Pros
    -0.08
    æĭŁ
    -0.08
    abus
    -0.08
     sleek
    -0.08
    éģįå¸ĥ
    -0.08
    POSITIVE LOGITS
    毫ä¸įçĬ¹è±«
    0.13
    å¾Ģå¾Ģ
    0.11
    ç«ĭåĪ»
    0.11
    åıĬæŶ
    0.11
    ç«ĭ马
    0.10
    ç«ĭåį³
    0.10
    派人
    0.10
    æ½
    0.10
    缸åºĶçļĦ
    0.10
    æĥ³åĬŀæ³ķ
    0.10
    Activations Density 0.119%

    No Known Activations