© 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. 7786
    Prev
    Next
    INDEX
    Explanations

    disembark into its floral

    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
    éĿŀ常éĩįè¦ģ
    -0.11
    PIP
    -0.10
    éĿŀ常好çļĦ
    -0.10
    æľī两个
    -0.10
    æľīå¾Īå¤ļç§į
    -0.09
     basically
    -0.09
    æľī两ç§į
    -0.09
    æĪijå½ĵæŶ
    -0.09
    bucks
    -0.08
    æľīå¾Īå¤ļ
    -0.08
    POSITIVE LOGITS
    éļ¾æĢª
    0.10
    ä¸ĢæŦ
    0.10
    åį³ä¾¿æĺ¯
    0.09
    åį³ä¾¿
    0.09
    èĢĮ对äºİ
    0.09
    ä½ķåĨµ
    0.08
    ç¨ļ
    0.08
    è¿Īåĩº
    0.08
    åıĪæĺ¯
    0.08
    ä¸Ģçķª
    0.08
    Activations Density 0.309%

    No Known Activations