© 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. 4637
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    çļĦæĺ¯
    -0.09
    “
    -0.09
    ramer
    -0.09
    æĪIJäºĨ
    -0.09
    æľīäºĨ
    -0.08
    身边çļĦ
    -0.08
    èĤī
    -0.08
    ester
    -0.08
    iens
    -0.08
     breathed
    -0.08
    POSITIVE LOGITS
    èĥľä»»
    0.12
    æĶ¯æĴij
    0.11
    åºĶ对
    0.10
    è¿Ļç§įäºĭæĥħ
    0.10
    æıIJä¾Ľä¼ĺè´¨
    0.10
    æѤ类
    0.10
    æĬµæĮ¡
    0.09
    å½ĵä¹ĭ
    0.09
    ä»Ģä¹Īéĥ½
    0.09
    带åĬ¨
    0.09
    Activations Density 0.046%

    No Known Activations