© 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. 14441
    Prev
    Next
    INDEX
    Explanations

    canon law and established representation

    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
    ukan
    -0.18
    inated
    -0.18
    æ®ĥ
    -0.18
    å¾·å·ŀ
    -0.18
    åľ»
    -0.18
    agne
    -0.17
    brains
    -0.17
    åijľ
    -0.17
    头ä¸Ĭ
    -0.16
     Bulg
    -0.16
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.26
    éĢļãĤĬ
    0.19
    ities
    0.18
    ually
    0.18
    ically
    0.17
    /legal
    0.17
    -minded
    0.17
    izable
    0.17
    rb
    0.16
    ocale
    0.16
    Activations Density 0.005%

    No Known Activations