© 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. 13607
    Prev
    Next
    INDEX
    Explanations

    film or book titles

    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
     Busty
    -0.22
    à¸Ħà¸ĵะà¸ģรรม
    -0.21
    ä¾Ĺ
    -0.20
    loom
    -0.19
     Bernardino
    -0.19
    çļĦæĥħå½¢
    -0.19
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.19
    iant
    -0.18
    èŀŃ
    -0.18
    SKI
    -0.18
    POSITIVE LOGITS
    æį¢ä¸ª
    0.21
    ModelError
    0.20
    ArrayOf
    0.20
    -themed
    0.19
    çĶµå½±
    0.19
    çİ©æĦı
    0.19
    æ»
    0.18
    (seq
    0.18
    adx
    0.18
    é¢ĺæĿIJ
    0.17
    Activations Density 0.129%

    No Known Activations