© 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. 11733
    Prev
    Next
    INDEX
    Explanations

    incumbent politician

    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
    çļĦåĪ°æĿ¥
    -0.21
    æĦıè¯ĨåĪ°
    -0.19
    пÑĥÑģк
    -0.19
    å½ĵåľ°äºº
    -0.19
    纸ä¸Ĭ
    -0.19
    æĦıè¯Ĩ
    -0.19
    驹
    -0.19
    åĪļ
    -0.19
    ÑĢеб
    -0.18
    PERT
    -0.18
    POSITIVE LOGITS
    åĬŁ
    0.22
    mpl
    0.21
     incumb
    0.21
    çľŁäºº
    0.20
    æĭŁå®ļ
    0.20
    åłĤ
    0.20
    åĽĽå¹´
    0.20
     Stud
    0.20
    uve
    0.20
    CHANGE
    0.19
    Activations Density 0.023%

    No Known Activations