© 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. 13933
    Prev
    Next
    INDEX
    Explanations

    turnovers, points, interceptions, ball

    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
    éĺ»åĬĽ
    -0.20
    认为
    -0.19
    ç±į
    -0.19
    suming
    -0.18
    æ°´æ³¥
    -0.18
    éĺ´å½±
    -0.17
    å§Ķæīĺ
    -0.17
    ä¸ĢæŃ¥
    -0.17
    odef
    -0.17
    _THREADS
    -0.17
    POSITIVE LOGITS
    è²łãģij
    0.21
    æĬł
    0.19
    天ä¸ĭ
    0.19
    OnError
    0.19
    çīµå¼ķ
    0.19
    两大
    0.18
     Huss
    0.18
    uden
    0.18
    çľĩ
    0.18
    èīĦ
    0.18
    Activations Density 0.001%

    No Known Activations