© 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. 37532
    Prev
    Next
    INDEX
    Explanations

    just or only

    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
    Dragging
    -0.10
    ÑĪка
    -0.09
    æĭ¨
    -0.09
    Nguá»ĵn
    -0.09
     Vivo
    -0.09
    æĴĩ
    -0.09
    URING
    -0.09
     KING
    -0.09
    леж
    -0.08
    thon
    -0.08
    POSITIVE LOGITS
    ä¸įæĺ¯ä¸Ģ个
    0.09
    第ä¸Ģéĥ¨
    0.09
    ä¸Ģ个æĸ°çļĦ
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    æ¡Ģ
    0.08
    çļĦåĬ¨åĬĽ
    0.08
    è¿Ļ段æŶéĹ´
    0.08
     кÑĥда
    0.08
    èѦåijĬ
    0.08
    hin
    0.08
    Activations Density 0.091%

    No Known Activations