© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12568
    Prev
    Next
    INDEX
    Explanations

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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»ĵæŀľæĺ¾ç¤º
    -0.20
    çļĦæľºä¼ļ
    -0.20
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.19
     masturbating
    -0.18
    æĦıä¹īä¸ĬçļĦ
    -0.18
    _waiting
    -0.18
    åįĬ个
    -0.18
     fashioned
    -0.17
    åı¯ä»¥è¯´æĺ¯
    -0.17
    æĽ´å¤ļçļĦæĺ¯
    -0.17
    POSITIVE LOGITS
    å°Ĩ
    0.23
    æıIJä¾Ľ
    0.23
    ied
    0.22
    ä¿ĿæĮģ
    0.21
    åĬ¨åijĺ
    0.19
    让
    0.19
    è¿Ľè¡Į
    0.19
    à¸Ĥà¸Ļา
    0.19
    æĬĬ
    0.19
    ays
    0.19
    Activations Density 0.119%

    No Known Activations