© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51348
    Prev
    Next
    INDEX
    Explanations

    Communist Party of China

    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
    顾
    -0.10
     ÙħÙĤ
    -0.10
    宿
    -0.09
    诧
    -0.09
     اÙĦÙħÙĤ
    -0.09
    管çIJĨ人åijĺ
    -0.09
     اÙĦبÙĬت
    -0.08
    สว
    -0.08
    磾
    -0.08
    管çIJĨåĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    ç§ijåѦåıijå±ķ
    0.13
    èĤī
    0.09
    è¢į
    0.09
    èĥĸ
    0.09
    ulled
    0.09
    æĭī
    0.09
    çĶ³åįļ
    0.09
    è±ļ
    0.09
    æĸ°åĨľæĿij
    0.09
    ritic
    0.08
    Activations Density 0.070%

    No Known Activations