© 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. 15851
    Prev
    Next
    INDEX
    Explanations

    private/independent educational institutions

    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
    éĴĿ
    -0.23
    ä¸īåĨľ
    -0.19
    stakes
    -0.19
    ç³Łç³ķ
    -0.19
    /release
    -0.19
    éĩĬ
    -0.18
    gend
    -0.18
    俳
    -0.18
    ranges
    -0.18
    æŶèĬĤ
    -0.17
    POSITIVE LOGITS
    ç§ģç«ĭ
    0.28
     schools
    0.24
     school
    0.24
    .Private
    0.23
    Private
    0.23
    /private
    0.22
    æ°ijåĬŀ
    0.22
     Private
    0.22
    ç§ģ人
    0.22
    åŃ¦æł¡
    0.21
    Activations Density 0.011%

    No Known Activations