© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12576
    Prev
    Next
    INDEX
    Explanations

    Nobel Peace Prize

    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
    æºIJæºIJä¸įæĸŃ
    -0.23
    大纲
    -0.21
    Elite
    -0.20
    å§Ĵ
    -0.20
    éĹ½
    -0.20
    æĻ¯å¾·
    -0.20
    æºIJæºIJ
    -0.19
    æĻ®æŁ¥
    -0.19
    æĵĬ
    -0.19
    éĵİ
    -0.19
    POSITIVE LOGITS
    人æĿĥ
    0.24
     humanitarian
    0.21
     activism
    0.21
    è··
    0.20
    .cancel
    0.20
     Baba
    0.20
     Peace
    0.20
    èĩªæķij
    0.19
    ially
    0.19
     peace
    0.19
    Activations Density 0.010%

    No Known Activations