© 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. 22448
    Prev
    Next
    INDEX
    Explanations

    history and medicine

    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
    æĭ¾
    -0.09
    æĶ¾æĿ¾
    -0.09
    鬣
    -0.09
    ç¿ĺ
    -0.09
    éķ°
    -0.09
     اÙĦعب
    -0.08
    æľīå¤ļ大
    -0.08
    æ°´åĩĨ
    -0.08
    æį¡
    -0.08
    åĢ¼å¾Ĺä¸Ģ
    -0.08
    POSITIVE LOGITS
    åºľ
    0.10
    à¸Ńาà¸ģาศ
    0.09
    emp
    0.09
    _SR
    0.09
     воздÑĥÑħ
    0.08
    bonus
    0.08
     squirt
    0.08
    евиÑĩ
    0.08
    åįĩåįİ
    0.08
    åĽŃåĮº
    0.08
    Activations Density 0.069%

    No Known Activations