© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20915
    Prev
    Next
    INDEX
    Explanations

    I amshe iswe are

    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
    çļĦåIJĦç§į
    -0.10
    éĤ£ä¹Īå¤ļ
    -0.10
    éĤ£ç§į
    -0.09
    onden
    -0.09
    ilo
    -0.09
    ç²¾æ¹Ľ
    -0.09
    alytics
    -0.08
    hum
    -0.08
    bas
    -0.08
    éģ®
    -0.08
    POSITIVE LOGITS
    æĬĵç´§
    0.09
    æŀģ为
    0.09
    ä¸įå°ij
    0.09
    æŀģæĺĵ
    0.09
    缸å½ĵ
    0.09
    æŀģ大
    0.09
    ä¸ŀ
    0.09
    è¹Ĭ
    0.09
    åħļåĨħ
    0.08
    achs
    0.08
    Activations Density 0.224%

    No Known Activations