© 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. 16020
    Prev
    Next
    INDEX
    Explanations

    Ch` followed by `ampionship`

    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
     годÑĭ
    -0.23
    éľĸ
    -0.20
     cup
    -0.20
    Years
    -0.20
    gere
    -0.20
     years
    -0.20
    éĢIJå¹´
    -0.19
    åīįåIJİ
    -0.19
    æĬĬè¿ĻäºĽ
    -0.19
    æĽ¾
    -0.19
    POSITIVE LOGITS
    æľ¬åij¨
    0.30
    æĸ°ä¸Ģè½®
    0.24
    æľ¬æľĪ
    0.23
    ä¾Ŀæŧæĺ¯
    0.22
    继ç»Ńä¿ĿæĮģ
    0.22
    æĸ°çļĦä¸Ģ
    0.22
    ä¸İæѤåIJĮæŶ
    0.21
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.21
    æĸ°çļĦ
    0.20
    èѦæĥķ
    0.20
    Activations Density 0.070%

    No Known Activations