© 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. 14808
    Prev
    Next
    INDEX
    Explanations

    digits and periods

    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
     BOX
    -0.19
    ubs
    -0.19
    werk
    -0.19
    etz
    -0.19
     sometime
    -0.18
     Hunts
    -0.18
    ume
    -0.18
    kle
    -0.17
     umbrella
    -0.17
    é¢ĦæĬ¥
    -0.17
    POSITIVE LOGITS
    社ä¼ļæķĪçĽĬ
    0.20
    åĽ½åĨħå¸Ĥåľº
    0.20
    ãģ£ãģ
    0.20
    çĽ´è¾¾
    0.19
    åľ¨éĩĮéĿ¢
    0.19
    æĨ¾
    0.19
    åľ¨åºĬä¸Ĭ
    0.19
    æĮĪ
    0.19
    å°ıå§IJå§IJ
    0.18
    åĢĻ
    0.18
    Activations Density 0.016%

    No Known Activations