© 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. 10805
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    çİ°åľ¨å·²ç»ı
    -0.24
    æĸ¹
    -0.20
    æĭĶ
    -0.19
    çļĦå°±æĺ¯
    -0.19
    åįģäºĮ
    -0.18
    æijĨ
    -0.18
    æĸ¹åı¯
    -0.17
    象
    -0.17
    çļĦå£°éŁ³
    -0.17
    æĸ¯
    -0.17
    POSITIVE LOGITS
    éķı
    0.20
    _PRIORITY
    0.19
    olly
    0.19
    esan
    0.19
    åķĦ
    0.19
    enses
    0.18
    chten
    0.17
    аÑĢÑĮ
    0.17
    çķĽ
    0.17
    浪
    0.17
    Activations Density 0.028%

    No Known Activations