© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    Senate election

    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
    æ¯ıèĤ¡
    -0.20
     ÙħÙĨزÙĦ
    -0.20
    çĽ¼
    -0.20
    鼶è·Ŀ离
    -0.19
    è¿Ļè¯Ŀ
    -0.19
    åħ¨å¸Ĥ
    -0.19
    ç»ĨåĪĨ
    -0.19
    æĭ¾
    -0.19
    æķ´æ´ģ
    -0.19
    ç§ģæľį
    -0.19
    POSITIVE LOGITS
    DidChange
    0.22
    æİī
    0.21
    åѤç«ĭ
    0.20
    çľŁäºº
    0.20
    åı²è¯Ĺ
    0.19
    (cos
    0.19
    ç¾İåĽ½äºº
    0.19
     decades
    0.19
    éĴĹ
    0.19
     heav
    0.19
    Activations Density 0.039%

    No Known Activations