© 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. 27961
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    ibly
    -0.10
    头顶
    -0.10
    ä¹ĭä½Ļ
    -0.10
    arily
    -0.09
    éĢıè¿ĩ
    -0.09
    躺çĿĢ
    -0.09
    æį®æѤ
    -0.09
    .getRaw
    -0.09
    æĢ§å¼º
    -0.09
    оÑĢо
    -0.09
    POSITIVE LOGITS
    åIJį声
    0.10
    çĶŁçĶŁ
    0.08
    æ¼ķ
    0.08
    æĢ¨
    0.08
    åľ¨çİ°åľº
    0.08
     Menu
    0.08
    itzer
    0.08
    认åı¯
    0.08
    èIJ½åľ¨
    0.08
     menu
    0.08
    Activations Density 0.039%

    No Known Activations