© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    0 followed by 1 or

    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
    BOR
    -0.20
    .SDK
    -0.19
     влаÑģÑĤи
    -0.18
     Rudy
    -0.18
    ä¾Ŀ
    -0.17
     sut
    -0.17
    âİŁ
    -0.17
     ÑĩаÑģÑĤ
    -0.17
    ä¸įåĪ°
    -0.17
     theorem
    -0.17
    POSITIVE LOGITS
    æĤłæĤł
    0.21
    Performed
    0.20
    æĹ¥æĬ¥è®°èĢħ
    0.19
    æīĢæīĢ
    0.19
    å¿Ŀ
    0.19
    æ®ģ
    0.18
    èĽ¤
    0.18
    æĢĢæĬ±
    0.18
    踵
    0.18
    ¡´
    0.17
    Activations Density 0.120%

    No Known Activations