© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    democracy, governor, elections

    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
    æĢĴ
    -0.20
    çļĦæĢ§æł¼
    -0.18
     Washer
    -0.17
    ä¸ĢåĪĩ
    -0.17
     NRL
    -0.17
    TC
    -0.17
     attitude
    -0.17
    bbie
    -0.17
    uvo
    -0.17
    èĦı
    -0.16
    POSITIVE LOGITS
    idget
    0.20
    æ¡ĮéĿ¢
    0.19
    жÑĥ
    0.18
    oley
    0.17
    é£ĵ
    0.17
    DAC
    0.17
    .signal
    0.17
    uran
    0.17
    ç½ij游
    0.17
    çĻ»ä¸Ĭ
    0.17
    Activations Density 0.001%

    No Known Activations