© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    F1 drivers and statistics

    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
    ä¸Ģç»ı
    -0.22
    ALA
    -0.20
    perature
    -0.19
    repos
    -0.18
    pra
    -0.18
    omit
    -0.18
    ugi
    -0.18
    æ¼ķ
    -0.18
    Hooks
    -0.18
    åĪ¶ä½ľ
    -0.18
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.21
    è¤
    0.20
    年度
    0.20
    éĺµèIJ¥
    0.20
    ãģĦãĤĭ
    0.20
    æľĢå¿«çļĦ
    0.18
    æ¯Ķäºļ
    0.17
    æĢ»åĨłåĨĽ
    0.17
    ä¸ī大
    0.17
    é¦ĸ缸
    0.17
    Activations Density 0.007%

    No Known Activations