© 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. 54501
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    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
    è¿«ä¸įåıĬ
    -0.09
    å°±æѤ
    -0.09
    getManager
    -0.09
    éļ¾æĢª
    -0.09
    _Find
    -0.09
     Bedford
    -0.09
    åĹŁ
    -0.08
    WithValue
    -0.08
    è¶Ĭ好
    -0.08
     ultimately
    -0.08
    POSITIVE LOGITS
    åIJĮæł·æĺ¯
    0.22
    åIJĮæł·
    0.21
     ebenfalls
    0.20
    åIJĮæł·çļĦ
    0.18
    ä¹ŁåIJĮæł·
    0.17
     ìĹŃìĭľ
    0.17
    åIJĮ樣
    0.17
     ÑĤоже
    0.15
     likewise
    0.15
    ä¹Łæĺ¯å¦ĤæѤ
    0.13
    Activations Density 0.338%

    No Known Activations