© 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. 11474
    Prev
    Next
    INDEX
    Explanations

    academic and research topics

    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
    æŃ¤æ¬¡æ´»åĬ¨
    -0.25
    è£ħå¤ĩåĪ¶éĢł
    -0.24
    为éĩįçĤ¹
    -0.23
    åħ¨éķĩ
    -0.22
    å·²äºİ
    -0.22
    çĶŁäº§å·¥èīº
    -0.22
    åİŁæłĩé¢ĺ
    -0.21
    çİ°åľ¨å·²ç»ı
    -0.21
    为主é¢ĺ
    -0.21
    åĢ¼å¾Ĺåħ³æ³¨
    -0.21
    POSITIVE LOGITS
    å¾Īå¤ļæŶåĢĻ
    0.25
    大å¤ļ
    0.25
     purely
    0.24
     ÐĶм
    0.23
    å¾Ģå¾Ģ
    0.23
     ÐIJлекÑģан
    0.23
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.23
     truly
    0.22
     like
    0.22
    å¾Īå¤ļ
    0.22
    Activations Density 0.205%

    No Known Activations