© 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. 16520
    Prev
    Next
    INDEX
    Explanations

    any kind

    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
    	TokenName
    -0.20
    æĺ¯ä¸Ģ款
    -0.19
    ames
    -0.19
    转身
    -0.19
    oran
    -0.19
    aber
    -0.18
    gon
    -0.18
    ãĥ¼ãĥ³
    -0.18
    éķ¿éķ¿
    -0.18
     أع
    -0.18
    POSITIVE LOGITS
    ä¸įçķĻ
    0.21
    ality
    0.20
    ilers
    0.19
    ilo
    0.18
    æĢ§è´¨
    0.18
    ularity
    0.17
     (*.
    0.17
     usual
    0.17
     ilk
    0.17
    å½¢å¼ı
    0.17
    Activations Density 0.048%

    No Known Activations