© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    San followed by place 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
    NEL
    -0.21
    æĢ§å¼º
    -0.20
     ÐŁÐ¾Ñĩем
    -0.20
    isk
    -0.19
    uffer
    -0.19
     ÐIJлекÑģан
    -0.19
    æĢ§çļĦ
    -0.19
    ensor
    -0.19
    kit
    -0.18
    ful
    -0.18
    POSITIVE LOGITS
    CodeAt
    0.19
     Bay
    0.19
    /goto
    0.18
    西路
    0.18
    _equalTo
    0.18
    åŁİå¸Ĥ
    0.17
    )section
    0.17
    æ¹¾åĮº
    0.17
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.17
    >NN
    0.17
    Activations Density 0.052%

    No Known Activations