© 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. 13065
    Prev
    Next
    INDEX
    Explanations

    office, constituents, and staffer

    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
    æľ¬åħ¬åı¸
    -0.19
    åħ¼
    -0.19
    ë¹Ī
    -0.19
    _BOOK
    -0.18
    ä¸įåIJĪ
    -0.18
    é»ijçĻ½
    -0.18
    ä¼ģä¸ļåľ¨
    -0.18
     sla
    -0.18
     Sloan
    -0.17
     дог
    -0.17
    POSITIVE LOGITS
    å·¥ä½ľäººåijĺ
    0.22
    åĬ©æīĭ
    0.21
    å·¥ä½ľæķĪçİĩ
    0.20
    æĹ¥å¸¸å·¥ä½ľ
    0.20
     staffer
    0.20
    åģļå¾Ĺ
    0.19
    åİ»åģļ
    0.19
    bsub
    0.19
    PIO
    0.19
     Races
    0.19
    Activations Density 0.024%

    No Known Activations