© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    positional or qualitative adjective + noun

    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
    aupt
    -0.23
    ÑĩÑĢежден
    -0.23
     ÑĦоÑĢмиÑĢова
    -0.21
    laus
    -0.21
     моÑīн
    -0.20
     кнопк
    -0.20
    æ³ķå®ĺ
    -0.20
     наÑĢко
    -0.20
    aign
    -0.20
     Clim
    -0.19
    POSITIVE LOGITS
    achinery
    0.26
     sciences
    0.22
    ä¸ļæĢģ
    0.22
     дело
    0.21
     ali
    0.21
    вед
    0.19
    inery
    0.19
    ä½ĵ系建设
    0.19
    æľįåĬ¡ä½ĵç³»
    0.19
     arts
    0.19
    Activations Density 0.287%

    No Known Activations