© 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. 10663
    Prev
    Next
    INDEX
    Explanations

    civil liberties, society, war, rights, emergencies, engineering, aviation, servant

    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
    à¹Ħหà¸Ļ
    -0.18
    æĹłç©·
    -0.17
    infinity
    -0.16
     ÐIJлекÑģан
    -0.16
    ige
    -0.16
    addle
    -0.16
    ever
    -0.16
    iggins
    -0.16
    IONS
    -0.16
    ä¼ļåIJĮ
    -0.15
    POSITIVE LOGITS
    ly
    0.23
    -minded
    0.21
    è¡·
    0.19
     minded
    0.19
    ucci
    0.18
    裳
    0.18
    ãģĹãģ¾ãģĦ
    0.18
    Ùij
    0.17
    ìį¨
    0.17
    ities
    0.17
    Activations Density 0.007%

    No Known Activations