© 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. 13490
    Prev
    Next
    INDEX
    Explanations

    century or -century followed by a noun

    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¯ı次
    -0.22
    ä»Ĭå¹´
    -0.21
    åŀĭä¼ģä¸ļ
    -0.20
    à¹Ĩ
    -0.20
    ç¨ĭ度
    -0.20
    heet
    -0.19
    åݻ年
    -0.19
    ä»Ĭ年以æĿ¥
    -0.18
    ä¾
    -0.18
    æľ¬èµĽåŃ£
    -0.18
    POSITIVE LOGITS
     onwards
    0.24
    é£İè²Į
    0.22
    -era
    0.22
    å·¦åı³
    0.20
    /right
    0.19
    /month
    0.19
    ês
    0.18
    аÐ
    0.18
    isle
    0.18
     onward
    0.17
    Activations Density 0.015%

    No Known Activations