© 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. 16829
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and positions

    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
    åŀĤ
    -0.20
    宿
    -0.19
     organic
    -0.19
     jam
    -0.19
     Bates
    -0.18
    æĪIJç«ĭ
    -0.18
    enet
    -0.18
    halt
    -0.18
    à¸IJ
    -0.17
    $core
    -0.17
    POSITIVE LOGITS
    æįĨç»ij
    0.22
    åIJįé¢Ŀ
    0.20
    åĬ¨æijĩ
    0.19
    ç²¾åĩĨæī¶è´«
    0.19
    å¦ĤæľŁ
    0.19
    aired
    0.19
    ç»ıæµİæĬĢæľ¯
    0.19
    ç»ķ
    0.19
    çħ
    0.19
    èıĸ
    0.18
    Activations Density 0.007%

    No Known Activations