© 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. 14141
    Prev
    Next
    INDEX
    Explanations

    specific entities or 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
    arah
    -0.20
    ç»ıèIJ¥ç®¡çIJĨ
    -0.20
    anos
    -0.20
    åĽłä¸ºå®ĥ
    -0.19
    ä¸įä¸ĭ
    -0.19
    mate
    -0.19
    åīįå¤ķ
    -0.18
    spark
    -0.18
    uras
    -0.18
    å¿Ĺ强
    -0.18
    POSITIVE LOGITS
     Ritch
    0.23
    GLOBALS
    0.23
    /lic
    0.20
    æĢ§è´¨
    0.20
    opolitan
    0.19
    æ²ı
    0.19
    ä¸ĵåijĺ
    0.19
    Powered
    0.18
     ingl
    0.18
    iali
    0.18
    Activations Density 0.971%

    No Known Activations