© 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. 5707
    Prev
    Next
    INDEX
    Explanations

    country of origin

    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
    é¢ĺ主
    -0.09
    APA
    -0.09
    elix
    -0.09
    éĤ£æ¬¡
    -0.09
    楼主
    -0.09
    åħ¥ä¾µ
    -0.09
    åIJĮåѦ们
    -0.09
    è¦ģä¸įçĦ¶
    -0.09
    çݩ家们
    -0.09
    æĪijåĴĮ
    -0.09
    POSITIVE LOGITS
    lyph
    0.10
    atro
    0.10
    伤亡
    0.09
    æĭ¥æĮ¤
    0.09
    èĩªæĦ¿
    0.09
    ç±į
    0.09
    ç´łåħ»
    0.08
    URT
    0.08
    èĩªåıij
    0.08
    á¹Ģ
    0.08
    Activations Density 0.054%

    No Known Activations