© 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. 14555
    Prev
    Next
    INDEX
    Explanations

    Voltaire's plays, foreign words

    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
    InSection
    -0.19
     Cree
    -0.19
    ograms
    -0.18
     Nir
    -0.18
     Durham
    -0.18
    grams
    -0.18
    åĩĮæĻ¨
    -0.17
    å¯ĨéĽĨ
    -0.17
    ocode
    -0.17
    acr
    -0.17
    POSITIVE LOGITS
    anton
    0.20
    aten
    0.20
    аÑĤелÑĮ
    0.19
    殿ä¸ĭ
    0.18
    饺
    0.18
    è¯Ħè®®
    0.18
    æĭ³
    0.18
     sublicense
    0.18
    å°ıé¢Ŀ
    0.18
     Jacques
    0.18
    Activations Density 0.001%

    No Known Activations