© 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. 13974
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    tle
    -0.23
    åºŃ
    -0.20
    alled
    -0.20
    ì¤ĺ
    -0.19
    usty
    -0.18
    æĴŃ
    -0.18
    æĿŃ
    -0.18
     tick
    -0.18
    Ticks
    -0.18
     Busty
    -0.18
    POSITIVE LOGITS
     Anders
    0.20
     eve
    0.19
    åı²ä¸ĬæľĢ
    0.19
    åŃIJå¼¹
    0.19
    è°ij
    0.19
    ä¹ĭç±»çļĦ
    0.18
    çŃī诸å¤ļ
    0.18
    ä½ĵ积
    0.18
    รวม
    0.18
    好äºĭ
    0.17
    Activations Density 0.038%

    No Known Activations