© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    paste, pulp, or ketchup

    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
    çĿĽ
    -0.19
    extras
    -0.18
    inis
    -0.18
    ä¸įåĬ¨
    -0.17
    inic
    -0.17
    æľ¬äºº
    -0.17
    失信
    -0.17
    enne
    -0.17
    èĩªä¸»
    -0.17
    ovy
    -0.17
    POSITIVE LOGITS
    å¥ı
    0.19
    ä¸ĢéĹ´
    0.19
    éģ¿
    0.18
    å¸ĥå°Ķ
    0.18
    nil
    0.18
    _yaw
    0.18
    embedded
    0.18
    оваÑĢ
    0.18
    é¢ľ
    0.17
    ucker
    0.17
    Activations Density 0.003%

    No Known Activations