© 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. 13150
    Prev
    Next
    INDEX
    Explanations

    sports events and locations

    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
    æ±Ĭ
    -0.23
    ä¸ĸä¸Ĭ
    -0.19
    æī§ä¸ļ
    -0.18
    为æ°ij
    -0.18
    cles
    -0.18
    èĢĺ
    -0.18
    upe
    -0.18
     heel
    -0.17
    åľ¨åħ¨åĽ½
    -0.17
    .Dispatch
    -0.17
    POSITIVE LOGITS
     Mounted
    0.20
    (auto
    0.19
    缸å½ĵäºİ
    0.19
    åĽĽåŃ£
    0.19
     Jad
    0.18
    éĻ¤éĿŀ
    0.18
    IEW
    0.18
    éĥĬ
    0.18
    æ½ŀ
    0.18
    强èĢħ
    0.17
    Activations Density 0.001%

    No Known Activations