© 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
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    international students

    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
    æĹ¥å¸¸å·¥ä½ľ
    -0.20
    æĢ»çĽij
    -0.20
    неж
    -0.19
    iban
    -0.19
     Tac
    -0.18
     обÑĬÑıвл
    -0.18
    APH
    -0.18
    -property
    -0.18
    ä¸ĩç§ij
    -0.17
    liv
    -0.17
    POSITIVE LOGITS
    åŃ¦è´¹
    0.24
    æĪ·ç±į
    0.23
    åIJĮåѦ
    0.22
    åħ¨æĹ¥åĪ¶
    0.21
    referer
    0.21
    æĬķ
    0.20
    åħ¥åѦ
    0.20
     students
    0.19
    以å¤ĸ
    0.19
    æĭĽçĶŁ
    0.19
    Activations Density 0.013%

    No Known Activations