© 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. 27341
    Prev
    Next
    INDEX
    Explanations

    financial year

    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
    ä¸įçŁ¥
    -0.11
    åķĨä¸ļåĮĸ
    -0.09
    ÑģÑĤо
    -0.09
    ä¸įçŁ¥éģĵ
    -0.09
    æĹ¥åIJİ
    -0.08
    åįģ足
    -0.08
    åºķå±Ĥ
    -0.08
    .cond
    -0.08
     Buckley
    -0.08
    ä¸įæĺİ
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦä¸Ģå¹´
    0.10
    æĸ°çļĦä¸Ģ
    0.09
    æĬ¥è¡¨
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    åĽŀ顾
    0.09
    媳
    0.09
    æĬ¥åijĬæľŁåĨħ
    0.09
    มà¸Ļ
    0.08
    åŃ£åº¦
    0.08
    çŀ»
    0.08
    Activations Density 0.079%

    No Known Activations