© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    say something about

    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
    .Kind
    -0.20
    åłĨæĶ¾
    -0.19
    è¦ģ注æĦı
    -0.19
    nis
    -0.19
    åı¯åľ¨
    -0.18
    éľĢ
    -0.18
     Ideas
    -0.18
    寸
    -0.18
    æĬĺ
    -0.18
     ideas
    -0.18
    POSITIVE LOGITS
    ç»Ŀ对ä¸įä¼ļ
    0.21
    isu
    0.20
    èĩªè±ª
    0.19
     truly
    0.19
     exper
    0.19
    ä¸įéĶĻçļĦ
    0.19
    ils
    0.19
    ä»ħ代表
    0.19
    ä½ĵéªĮ
    0.18
     certainly
    0.18
    Activations Density 0.023%

    No Known Activations