© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    numbers followed by million

    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
    èĭ¥å¹²
    -0.21
     disap
    -0.20
    igua
    -0.20
    人大
    -0.20
    ystack
    -0.19
    åŃĺ
    -0.19
    æĿĵ
    -0.18
    <w
    -0.18
    è¹ĩ
    -0.17
     thảo
    -0.17
    POSITIVE LOGITS
    ä¸ĸçķĮ第ä¸Ģ
    0.22
    ories
    0.19
    é¦ĸè½®
    0.19
    pit
    0.19
     Confidential
    0.18
    ä½į
    0.18
     ris
    0.17
    æµħ
    0.17
    ä¹ĭ称
    0.17
    cord
    0.17
    Activations Density 0.169%

    No Known Activations