© 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. 63253
    Prev
    Next
    INDEX
    Explanations

    payment to England

    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
    æѦèѦ
    -0.08
    æĪijä»¬ä¹Ł
    -0.08
    æİĮ声
    -0.08
    颦
    -0.07
    çĿģå¼Ģ
    -0.07
    ä¸Ģç§į
    -0.07
    亿ä¸ĩ
    -0.07
    æ²ı
    -0.07
    æĪij说
    -0.07
    ÑĤин
    -0.07
    POSITIVE LOGITS
    OST
    0.10
     ost
    0.10
    æ±Łæ·®
    0.09
    åĶĨ
    0.09
    è°ĭåĪĴ
    0.09
    åijĪ
    0.09
    ç¾İè²Į
    0.09
    çļĦè¶ĭåĬ¿
    0.09
    ORE
    0.09
    缣
    0.09
    Activations Density 0.285%

    No Known Activations