© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    sports statistics and competition

    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
    潺
    -0.21
     vulnerability
    -0.19
     capacities
    -0.19
    bib
    -0.19
     Vulner
    -0.18
    pra
    -0.18
    ISTA
    -0.18
    æ¼ıæ´ŀ
    -0.18
     mặc
    -0.18
    è¿«
    -0.17
    POSITIVE LOGITS
    æĶ¯éħį
    0.22
    arians
    0.20
     dominance
    0.19
    è·¬
    0.19
    çī¯
    0.18
    æľīäºĨ
    0.18
     ÐĵÑĢ
    0.17
     majority
    0.17
     quint
    0.17
    ChangedEventArgs
    0.17
    Activations Density 0.006%

    No Known Activations