© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    nuclear development and capabilities

    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
    ä¿Ŀ驾æĬ¤
    -0.24
    温æŁĶ
    -0.23
    害ç¾ŀ
    -0.23
    秩
    -0.20
    ãģĬãģĻãģĻ
    -0.20
    åIJĮè¡Į
    -0.20
    温馨
    -0.19
    aldo
    -0.19
    ÑĩаÑģÑĤ
    -0.19
    asio
    -0.19
    POSITIVE LOGITS
    çĶŁäº§
    0.27
    æĶ¹éĢł
    0.26
    Ħ件
    0.25
     components
    0.23
     production
    0.23
    åĪ¶éĢł
    0.21
    åİŁæĸĻ
    0.21
    æ°ijå¿ĥ
    0.20
    èĬ¯
    0.20
    ç»Ħ件
    0.20
    Activations Density 0.004%

    No Known Activations