© 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. 10618
    Prev
    Next
    INDEX
    Explanations

    flotsam, jetsam, ocean debris

    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
    ulty
    -0.22
    togroup
    -0.21
    éĨª
    -0.21
    æıIJ款
    -0.21
     OVERRIDE
    -0.21
    è±®
    -0.21
    çıĴ
    -0.21
    âĨĺ
    -0.21
    éĹ®è¯¢
    -0.20
    é³Ł
    -0.20
    POSITIVE LOGITS
     debris
    0.24
    åŀĥåľ¾
    0.24
    å®ŀçī©
    0.23
    æį¡
    0.23
     ocean
    0.22
    æµ·æ´ĭ
    0.21
    surface
    0.21
    ä¸įåı¯æĢĿè®®
    0.21
    æ´ģ
    0.21
    å¿ĥçĸ¼
    0.20
    Activations Density 0.024%

    No Known Activations