© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    all or everyone

    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
    两个人
    -0.14
    两人
    -0.11
    两ä½į
    -0.10
    ì§ĢëıĦ
    -0.10
    两çĤ¹
    -0.09
    _mm
    -0.09
    两项
    -0.09
    è¿Ļ两个
    -0.08
    prise
    -0.08
    æĬ¥åijĬæĺ¾ç¤º
    -0.08
    POSITIVE LOGITS
    åIJĦæĸ¹
    0.14
    大家éĥ½
    0.13
    ä¸īæĸ¹
    0.13
     everyone
    0.13
     everybody
    0.13
    大家éĥ½åľ¨
    0.13
    åħ±åIJĮåĬªåĬĽ
    0.12
    åĽĽæĸ¹
    0.12
     Everybody
    0.12
    everyone
    0.12
    Activations Density 0.071%

    No Known Activations