© 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. 16939
    Prev
    Next
    INDEX
    Explanations

    long distance task description

    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
    antly
    -0.18
    -equipped
    -0.18
    ually
    -0.18
    ä¸İæŶ
    -0.18
    oled
    -0.17
    ï¸ı
    -0.17
     Rever
    -0.17
    rtle
    -0.17
    empre
    -0.17
    åĽ½
    -0.17
    POSITIVE LOGITS
    ware
    0.28
    å§Ķä¼ļ
    0.27
    ìŀ¥ìĿĦ
    0.20
    åįĥä¸ĩåĪ«
    0.20
    级以ä¸Ĭ
    0.20
    æ¦ľ
    0.20
    èij©
    0.20
    稿
    0.20
    สà¹Ģà¸ķ
    0.19
    plex
    0.19
    Activations Density 2.333%

    No Known Activations