© 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. 15717
    Prev
    Next
    INDEX
    Explanations

    Central Asian geography and names

    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
    ered
    -0.19
    ight
    -0.19
    æĿ¯
    -0.18
    ous
    -0.18
    寡
    -0.18
    è¾Ļ
    -0.18
     cascade
    -0.17
     hazard
    -0.17
    碰
    -0.17
    åĩŃ
    -0.17
    POSITIVE LOGITS
    对äºİæĪij们
    0.19
    CEED
    0.18
    豸
    0.18
    ieres
    0.18
    gil
    0.17
    à¥į
    0.17
    еннаÑı
    0.17
     пÑĢоÑĨ
    0.17
    寮
    0.17
    пи
    0.17
    Activations Density 0.001%

    No Known Activations