© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1171
    Prev
    Next
    INDEX
    Explanations

    award ceremony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸įåIJ«
    -0.26
    quine
    -0.24
    cycl
    -0.24
     shelters
    -0.23
    æĴŀ
    -0.23
    缮çļĦæĺ¯
    -0.23
    绣
    -0.23
     sÃłng
    -0.22
     deck
    -0.22
    å¦ĵ
    -0.22
    POSITIVE LOGITS
    çİ°åľº
    0.36
     ceremony
    0.31
    é¢ģå¥ĸ
    0.29
     awards
    0.29
    åĪ°åľº
    0.28
     award
    0.28
     ceremonies
    0.28
     awarded
    0.27
    èİ·å¥ĸ
    0.27
    åľ¨çİ°åľº
    0.27
    Activations Density 0.025%

    No Known Activations