© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ally/ically/urally

    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
    å¹²èĦĨ
    -0.20
    íĹĢ
    -0.20
    å¤ıæĹ¥
    -0.19
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.19
    æŶéĹ´åĨħ
    -0.19
    /ref
    -0.19
    æĬĬè¿Ļ个
    -0.18
    è¯Ŀ说
    -0.18
    çŁŃçŁŃ
    -0.18
    äº²çľ¼
    -0.18
    POSITIVE LOGITS
     minded
    0.24
     speaking
    0.21
    åĴĮæĬĢæľ¯
    0.18
    /ge
    0.18
    -speaking
    0.18
    ÑįÑĤаж
    0.18
    ë§Į
    0.18
    /math
    0.18
     завиÑģим
    0.18
    -economic
    0.17
    Activations Density 0.106%

    No Known Activations