© 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. 12173
    Prev
    Next
    INDEX
    Explanations

    such ... changes, measurements, restoration, data, operations, desirable, molecular, devices, sensors

    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
    è¿Ļç¯ĩ
    -0.22
    ãģĿãĤĮãģŀãĤĮ
    -0.21
     iNdEx
    -0.20
     hereby
    -0.20
     ardından
    -0.18
    è¿Ļåĩłå¹´
    -0.18
    (propertyName
    -0.18
    ãģĿãĤĮãĤĴ
    -0.18
    enaries
    -0.18
    å¾Īéķ¿
    -0.18
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.31
    åģļæ³ķ
    0.26
    ç±»åŀĭçļĦ
    0.26
    æĥħå½¢
    0.25
     ÐIJлекÑģан
    0.21
    ness
    0.21
    ring
    0.20
    称åij¼
    0.20
    ãĤıãģijãģ§
    0.20
    举åĬ¨
    0.20
    Activations Density 0.061%

    No Known Activations