© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    prevent unintended damage

    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
    èĢĮéĿŀ
    -0.23
    èĢĮä¸įæĺ¯
    -0.22
    å¾Īå°ij
    -0.21
    åĢ¼å¾Ĺ
    -0.20
    ãģĤãĤĬ
    -0.20
    ä¸įæŃ¢
    -0.20
    almost
    -0.20
    éļIJ约
    -0.20
    åĩłä¹İ
    -0.19
    大æĸ¹
    -0.19
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.36
     anymore
    0.35
    æľīä»»ä½ķ
    0.35
    ä¸įå¿ħè¦ģçļĦ
    0.29
     nor
    0.29
    ä¹Łä¸įè¦ģ
    0.25
    èĢĮæĺ¯
    0.24
    ä»»ä½ķå½¢å¼ı
    0.24
    太ä¹ħ
    0.24
    ä»»ä½ķ人
    0.24
    Activations Density 0.201%

    No Known Activations