© 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. 14361
    Prev
    Next
    INDEX
    Explanations

    made his debut

    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
    è¿Ļ家åħ¬åı¸
    -0.21
    å°ıäºĭ
    -0.19
    å°ı游æĪı
    -0.19
     WithEvents
    -0.19
    ç¡®è¯Ĭ
    -0.19
    Units
    -0.19
    æ¯ıä¸Ģ天
    -0.19
    éĿ¢è²Į
    -0.18
    åĬŀ好
    -0.18
    å®īæİĴ
    -0.18
    POSITIVE LOGITS
    çݲ
    0.21
    -than
    0.20
     ÑĩиÑģл
    0.20
    åıĮéĩį
    0.19
     "('
    0.19
    ᶣ
    0.19
    å¤ļéĩį
    0.19
     "'.
    0.18
     anti
    0.18
    âĨĽ
    0.18
    Activations Density 0.622%

    No Known Activations