© 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. 11748
    Prev
    Next
    INDEX
    Explanations

    licenses, rights, Foundation, blog

    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
    好äºĭ
    -0.16
     веÑĩ
    -0.15
    åı£æ°Ķ
    -0.15
    éķ¿éķ¿
    -0.15
    ĵį
    -0.15
    éĿ©
    -0.15
    æŀķ头
    -0.15
    èĭŀ
    -0.15
    ä¸Ģ个èģĮä¸ļ
    -0.15
    åįİå°Ķ
    -0.15
    POSITIVE LOGITS
     пÑĢиÑıÑĤн
    0.18
    æ·¡
    0.16
    æ¶Ī
    0.16
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.16
    enge
    0.16
    ...)↵
    0.15
    Dist
    0.14
     педаг
    0.14
    à¸Ħะà¹ģà¸Ļ
    0.14
     ...
    0.14
    Activations Density 8.256%

    No Known Activations