© 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. 16016
    Prev
    Next
    INDEX
    Explanations

    Ryder Cup, Davis Cup

    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
     ÑĤоÑĢ
    -0.20
    &m
    -0.20
    çļĦ女åĦ¿
    -0.17
    _rules
    -0.17
    qml
    -0.17
    óg
    -0.17
    gere
    -0.17
    æķĻè®Ń
    -0.17
    .begin
    -0.16
     DFS
    -0.16
    POSITIVE LOGITS
    æĬij
    0.21
    ä½İ温
    0.19
    pen
    0.19
    港åĮº
    0.19
     pari
    0.18
    èļĮ
    0.18
    å¸ģ
    0.18
    åĬĪ
    0.18
    ä¸¤åľ°
    0.18
    å»¶æľŁ
    0.18
    Activations Density 0.001%

    No Known Activations