© 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. 11944
    Prev
    Next
    INDEX
    Explanations

    code generation, binding, transceivers

    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
    poly
    -0.21
    æ¯ı
    -0.21
    èĽĭ
    -0.20
     poly
    -0.19
     CAS
    -0.19
    ryn
    -0.19
    YSIS
    -0.18
    hole
    -0.18
     AGE
    -0.18
     Teh
    -0.18
    POSITIVE LOGITS
    aju
    0.20
    SHOT
    0.19
    ä¸į代表
    0.19
    пиÑģÑĮ
    0.19
    .pair
    0.18
    FAULT
    0.18
    à¹Ģà¸Īà¸Ń
    0.18
    ạo
    0.17
    èµ
    0.17
    形象
    0.17
    Activations Density 0.116%

    No Known Activations