© 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. 52471
    Prev
    Next
    INDEX
    Explanations

    industry and commercial companies

    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
    missions
    -0.12
    ç»Ļ大家
    -0.09
    å®ŀçī©
    -0.09
    ç»ĻåĪ«äºº
    -0.09
    bal
    -0.09
    论
    -0.09
    pack
    -0.09
    æ´¹
    -0.09
    第ä¸ī个
    -0.08
    åĤĴ
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.10
    ç»ıèIJ¥èĢħ
    0.09
    人士
    0.09
    erek
    0.09
    åĮĸçļĦ
    0.09
    ç¡
    0.09
    æĢ»åħ¬åı¸
    0.09
    ç»ıèIJ¥
    0.08
    egr
    0.08
    åķĨä¸ļ
    0.08
    Activations Density 0.053%

    No Known Activations