© 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. 14382
    Prev
    Next
    INDEX
    Explanations

    moving around

    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
    ç°Ł
    -0.20
    -ever
    -0.18
    GST
    -0.18
    èĭŀ
    -0.18
    伫
    -0.17
    ä»İæĿ¥æ²¡
    -0.17
    åĪ¹éĤ£
    -0.17
     sled
    -0.17
    ortic
    -0.17
    æ°´æµģ
    -0.17
    POSITIVE LOGITS
    çļĦå½¢å¼ı
    0.18
    æĺ¤
    0.18
    ä¸Ģ线
    0.18
    ä¤
    0.18
    åĬŀæ³ķ
    0.18
     Mu
    0.17
    around
    0.17
    Around
    0.17
    zew
    0.17
    dispatcher
    0.17
    Activations Density 0.015%

    No Known Activations