© 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. 14781
    Prev
    Next
    INDEX
    Explanations

    measure indicator metric

    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
    çѱ
    -0.21
    寡
    -0.21
    æĸ°çļĦä¸Ģ
    -0.21
    ãĥİãĥ¼
    -0.20
    å·¥ä½ľç«Ļ
    -0.20
    符åIJĪæĿ¡ä»¶
    -0.19
    Coordinate
    -0.19
    æĴ¤éĶĢ
    -0.19
    æĸ°æ¨¡å¼ı
    -0.19
    ä½ıæĪ¿åħ¬ç§¯
    -0.18
    POSITIVE LOGITS
    è¡¡éĩı
    0.35
    æĮĩæłĩ
    0.34
     indicator
    0.32
     indicators
    0.32
     measures
    0.31
    åıįæĺł
    0.31
     whether
    0.27
     measure
    0.26
     metrics
    0.26
     overall
    0.25
    Activations Density 0.133%

    No Known Activations