© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56122
    Prev
    Next
    INDEX
    Explanations

    light-induced physical phenomena

    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
    éĢģæĿ¥
    -0.10
     Balt
    -0.09
    æµĨ
    -0.09
    ä¹Łä¸įæķ¢
    -0.09
    æĪ´
    -0.09
     Sham
    -0.08
    æı¡æīĭ
    -0.08
    é¢ĦèѦ
    -0.08
    /weather
    -0.08
     comer
    -0.08
    POSITIVE LOGITS
    壮
    0.10
    çŤ
    0.09
    çī¹å®ļ
    0.09
    壯
    0.09
    å¤§åľ°
    0.09
    åĽĽä¸ªèĩªä¿¡
    0.08
    æ¯Ķåĸ»
    0.08
    éĿĴéĵľ
    0.08
    AKE
    0.08
     Bison
    0.08
    Activations Density 0.199%

    No Known Activations