© 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. 16217
    Prev
    Next
    INDEX
    Explanations

    mobilize or organize efforts

    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
    ë°©ìĨ¡
    -0.22
    æľ
    -0.20
    鸵
    -0.19
    restore
    -0.19
    สาร
    -0.19
    etine
    -0.19
    符
    -0.18
    æĭħå¿ĥ
    -0.18
    et
    -0.18
    ç»ıèIJ¥çIJĨ念
    -0.18
    POSITIVE LOGITS
    åĬ¨åijĺ
    0.30
     mobil
    0.30
     campaign
    0.28
     Mobil
    0.27
    åĬĽéĩı
    0.27
    èµ·æĿ¥
    0.26
    èµ·æĿ¥äºĨ
    0.25
     campaigns
    0.24
    äºĨèµ·æĿ¥
    0.23
     Campaign
    0.23
    Activations Density 0.029%

    No Known Activations