© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    multiple selection

    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
    кÑģ
    -0.20
    éĻĦ
    -0.20
    rang
    -0.19
    vro
    -0.19
    æł·åŃIJ
    -0.19
    dux
    -0.18
    _First
    -0.18
    duct
    -0.18
    ç²īä¸Ŀ
    -0.18
    -books
    -0.18
    POSITIVE LOGITS
    åľ£åľ°
    0.19
    onde
    0.19
    并ä¸į代表
    0.18
    ç»Ļèĩªå·±
    0.17
     Wolfgang
    0.17
    æĪ¿ä¸ľ
    0.17
    ulis
    0.17
    bt
    0.17
    为ä¹ĭ
    0.17
    æľīæĿĥ
    0.17
    Activations Density 0.035%

    No Known Activations