© 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. 55981
    Prev
    Next
    INDEX
    Explanations

    reports summarizing studies

    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
    æ¯ıä¸Ģä½į
    -0.10
    çŁ¥éģĵèĩªå·±
    -0.10
    ï¸
    -0.10
     окÑĢÑĥжа
    -0.09
    _PD
    -0.09
    第ä¸ĢæŶéĹ´
    -0.09
    æ¯ıä¸Ģ个人
    -0.08
    дÑĥÑĪ
    -0.08
    åľ°ä¸Ĭ
    -0.08
    æĮ¥
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.14
    çłĶ究æĬ¥åijĬ
    0.12
    çłĶ究表æĺİ
    0.11
     studies
    0.10
    -reported
    0.09
     reported
    0.09
    çłĶ究
    0.09
    æĬ¥éģĵ称
    0.09
    æĸĩçĮ®
    0.09
     Authors
    0.09
    Activations Density 1.164%

    No Known Activations