© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17207
    Prev
    Next
    INDEX
    Explanations

    MADS or chrome wing

    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
    Negative Logits
    _REPLY
    -0.24
    imps
    -0.21
    ä»ģ
    -0.19
    Reply
    -0.19
    _reply
    -0.18
    åİ
    -0.18
     ActiveSupport
    -0.17
    åįľ
    -0.17
    ihar
    -0.17
    -system
    -0.17
    POSITIVE LOGITS
    åijĺ
    0.23
    ä¸ĵåijĺ
    0.20
    äºĨä¸Ģåı¥
    0.18
    ç²īèī²
    0.18
    ARB
    0.18
    Drivers
    0.18
    身份
    0.18
    atório
    0.18
    帳
    0.18
    ä¸į认è¯Ĩ
    0.17
    Activations Density 0.057%

    No Known Activations