© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    counting numbers before plurals

    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
    ippy
    -0.22
    ä»ħ代表
    -0.20
    Together
    -0.19
    åĬ¬
    -0.18
    ilib
    -0.18
    andel
    -0.17
    _collections
    -0.17
    é»Ķ
    -0.17
    áo
    -0.17
     помоÑīÑĮÑİ
    -0.17
    POSITIVE LOGITS
    à¸Ħะà¹ģà¸Ļ
    0.20
     pinch
    0.20
    ÑĩÑĢежден
    0.19
    èĥ½åľ¨
    0.19
     ÐIJлекÑģан
    0.19
    -than
    0.18
    -dollar
    0.18
    à¸Ĥà¸Ļา
    0.18
    详
    0.17
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.17
    Activations Density 0.033%

    No Known Activations