© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10561
    Prev
    Next
    INDEX
    Explanations

    national laboratory names

    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
    Negative Logits
    éĥ¨åī¯éĥ¨éķ¿
    -0.19
    ç§ijæĬĢ大åѦ
    -0.19
    ä¸ļ
    -0.18
    pler
    -0.17
    пÑĢакÑĤик
    -0.17
    -0.17
    WEBPACK
    -0.17
    渲
    -0.17
    omorphic
    -0.17
     Gould
    -0.17
    POSITIVE LOGITS
    chs
    0.18
    鸱
    0.18
    éĻĦè¿ijçļĦ
    0.17
    é©»æĿij
    0.17
    ISCO
    0.17
    нÑĭ
    0.17
    åºĦ严
    0.17
    áng
    0.17
    派驻
    0.17
    åħ¬åħ±
    0.17
    Activations Density 0.010%

    No Known Activations