© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    hra
    -0.09
    ullo
    -0.09
    Ļ¨
    -0.09
    iges
    -0.09
    rieve
    -0.08
     Hus
    -0.08
    æľ´
    -0.08
    è£ķ
    -0.08
     sometime
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    POSITIVE LOGITS
    ç§įç±»
    0.15
    å¤ļè¾¾
    0.15
    åĵģç§į
    0.14
    大大å°ıå°ı
    0.14
    æľīå¾Īå¤ļç§į
    0.12
    åįģåĩłä¸ª
    0.11
    ä¸ĬçĻ¾
    0.11
    大大å°ı
    0.11
    æľīå¤ļå°ij
    0.10
     dozens
    0.10
    Activations Density 0.193%

    No Known Activations