© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 15463
    Prev
    Next
    INDEX
    Explanations

    risk of conditions

    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
    æĪIJ为ä¸ĢåIJį
    -0.24
    æĪIJ为ä¸Ģ个
    -0.24
    æŃ£åľ¨è¿Ľè¡Į
    -0.23
     ÑģобÑģÑĤвенно
    -0.22
    åIJĦæł·
    -0.21
    æŃ£æĸĩ
    -0.21
    æ¯ıä¸Ģä½į
    -0.21
    æ¯ıä½į
    -0.21
    éĢ»è¾ij
    -0.20
    带åĽŀ
    -0.20
    POSITIVE LOGITS
    建åĨĽ
    0.23
     households
    0.20
    ucky
    0.20
     versus
    0.20
     intact
    0.19
     consistent
    0.19
     cÃłng
    0.19
    upt
    0.19
    æ¯Ķèµ·
    0.19
     household
    0.18
    Activations Density 0.473%

    No Known Activations