© 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. 51095
    Prev
    Next
    INDEX
    Explanations

    syntax highlighting code editor

    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
    鬼
    -0.10
     кли
    -0.10
    .libs
    -0.09
    æĪ·å¤ĸ
    -0.09
    çĵ¯
    -0.09
    ç´ĭ
    -0.09
    è¸ı
    -0.09
    æĿĸ
    -0.09
    åIJĮåŁİ
    -0.09
    Ùħج
    -0.09
    POSITIVE LOGITS
     code
    0.10
    gments
    0.09
    åºĸ
    0.09
    getCode
    0.09
    code
    0.09
    åı¼
    0.09
    _cod
    0.09
    CODE
    0.09
    cod
    0.09
    åī¥
    0.08
    Activations Density 0.202%

    No Known Activations