© 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. 11190
    Prev
    Next
    INDEX
    Explanations

    city connector

    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
    utow
    -0.21
    æĹ»
    -0.20
    iban
    -0.20
    åIJĮæĥħ
    -0.19
    éľİ
    -0.19
    ìŀIJìĿĺ
    -0.19
     commons
    -0.18
    crest
    -0.18
    ªĮ
    -0.18
    �t
    -0.18
    POSITIVE LOGITS
    '
    0.20
    ITS
    0.19
    ç»ıèIJ¥æ´»åĬ¨
    0.19
    绿水
    0.19
    rances
    0.18
    ä¼Ĺå¤ļ
    0.18
     McD
    0.18
    cribes
    0.18
    侯
    0.17
    å½±åĵįåĬĽ
    0.17
    Activations Density 0.080%

    No Known Activations