© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    preventing or stopping actions

    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
    ä½ľèĢħæľ¬äºº
    -0.18
    åľ°çIJĥä¸Ĭ
    -0.18
    çļĦä¿¡ä»»
    -0.17
    ultiply
    -0.17
    çļĦæĪ¿åŃIJ
    -0.17
     culmination
    -0.17
    éĢŁåº¦å¿«
    -0.17
    解æĶ¾æĢĿæĥ³
    -0.17
    ä¸įä¸Ģæł·çļĦ
    -0.16
    à¸ķรà¸ĩ
    -0.16
    POSITIVE LOGITS
    æĪIJ为
    0.29
     being
    0.27
     becoming
    0.23
    jang
    0.22
    æĪIJ为ä¸Ģ个
    0.21
    æľīä»»ä½ķ
    0.21
    æĪIJçĤº
    0.21
    /mit
    0.20
    tober
    0.19
     further
    0.19
    Activations Density 0.031%

    No Known Activations