© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9494
    Prev
    Next
    INDEX
    Explanations

    found, seen, made, studied, gathered

    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
     Od
    -0.09
    æľīèĥ½åĬĽ
    -0.08
    ä¸įä¸Ģå®ļ
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    initely
    -0.08
    ä¸Ģçķª
    -0.08
    åºĬä¸Ĭ
    -0.08
    èıŁ
    -0.08
     able
    -0.08
     enough
    -0.08
    POSITIVE LOGITS
    quil
    0.10
    éĢļè¿ĩ对
    0.09
     Kardash
    0.09
    ä¸ĭä¾Ĩ
    0.08
    ä¸ĭæĿ¥
    0.08
    åıijæĺİ
    0.08
    grav
    0.08
    åĴĭ
    0.08
    ardy
    0.08
    atoria
    0.08
    Activations Density 0.192%

    No Known Activations