© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11906
    Prev
    Next
    INDEX
    Explanations

    some or several things/items/ways/occasions

    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
    æĢ»ç®Ĺ
    -0.20
    åĪ°åºķæĺ¯
    -0.20
    åľ¨çİ°åľº
    -0.20
    æ¯ķç«Łæĺ¯
    -0.19
    ä»ĬåĽŀãģ¯
    -0.19
    æĪIJç«ĭäºİ
    -0.19
    ä¸ĩä¸Ģ
    -0.18
    è¿ĻéĩĮçļĦ
    -0.18
    éĥ½ä¼ļæľī
    -0.18
     herr
    -0.18
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.22
    æŶåĢĻ
    0.20
     ways
    0.20
    æĪij们å¿ħé¡»
    0.19
    æĥħåĨµä¸ĭ
    0.18
    ocop
    0.18
     occasions
    0.18
     way
    0.18
    MER
    0.18
    ntl
    0.18
    Activations Density 0.101%

    No Known Activations