© 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. 15172
    Prev
    Next
    INDEX
    Explanations

    music and creative works

    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
    æĸ°åĬ¨èĥ½
    -0.20
    ä¸Ģ个好çļĦ
    -0.19
    edis
    -0.19
    åĬłå¤§
    -0.19
    æĸ¹éĿ¢
    -0.18
     Bentley
    -0.18
    责任
    -0.18
    æľŁéĹ´
    -0.18
    ç¢Į
    -0.18
    èĭ«
    -0.18
    POSITIVE LOGITS
     вÑģегда
    0.24
    é£İæł¼
    0.21
    æĢ»æĺ¯
    0.21
    CEPT
    0.21
    大å¤ļæĺ¯
    0.20
    ä»İæĿ¥ä¸į
    0.20
    å¾Ģå¾Ģ
    0.20
    é¢¨æł¼
    0.20
     altijd
    0.20
    ç»Ĩèħ»
    0.20
    Activations Density 0.104%

    No Known Activations