© 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. 17214
    Prev
    Next
    INDEX
    Explanations

    bulk carriers

    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
    *↵
    -0.12
    -0.12
    ...↵
    -0.11
    âĢ¦↵
    -0.11
    -
    -0.11
    ...
    -0.10
     E
    -0.10
    [email
    -0.10
    1
    -0.10
     Agr
    -0.10
    POSITIVE LOGITS
     lesbische
    0.13
    ä¸»åľº
    0.12
    ç½ijé¦ĸ页
    0.12
    产ä¸ļåįĩ级
    0.12
    çŃīé¢ĨåŁŁ
    0.12
    åѤåĦ¿
    0.12
    客æĪ·æıIJä¾Ľ
    0.12
    娱ä¹IJåŁİ
    0.12
    è¡Įä¸ļåıijå±ķ
    0.12
    æ²³æµģåŁŁ
    0.12
    Activations Density 46.899%

    No Known Activations