© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4217
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun

    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
    ç§ijæĬĢæĪIJæŀľ
    -0.09
    累累
    -0.09
    åĴĮä»ĸçļĦ
    -0.09
    APPER
    -0.09
    æ³Ľ
    -0.08
    ights
    -0.08
    uess
    -0.08
    CTOR
    -0.08
    æĹ¢æĺ¯
    -0.08
    ori
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģéĥ¨åĪĨ
    0.13
    çļĦä¸Ģåijĺ
    0.12
    çļĦä¸Ģç§į
    0.12
    润æ»ij
    0.10
    ä¾Ŀæį®
    0.10
    çļĦä¸Ģ项
    0.10
    åĶ¯ä¸Ģ
    0.10
    çļĦä¸Ģ个
    0.10
    åİŁåĽłä¹ĭä¸Ģ
    0.10
     equivalent
    0.09
    Activations Density 0.214%

    No Known Activations