© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21914
    Prev
    Next
    INDEX
    Explanations

    composers and historical figures

    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
    å¾®ç¬ij
    -0.09
    Rated
    -0.09
     ÐŁÑĢе
    -0.08
     знаÑĩиÑĤ
    -0.08
    agher
    -0.08
    èIJĦ
    -0.08
    主æķĻç»ĥ
    -0.08
    /ic
    -0.08
    redi
    -0.08
    alus
    -0.08
    POSITIVE LOGITS
    æ°ijåĽ½
    0.11
    æľįåĬ¡è´¨éĩı
    0.10
     telegram
    0.09
    æ³ł
    0.09
    ç»ıåħ¸
    0.09
     Bols
    0.09
    èµ·æĿ¥
    0.09
    æģ½
    0.09
    ç»ıåħ¸çļĦ
    0.09
    纪念é¦Ĩ
    0.09
    Activations Density 0.239%

    No Known Activations