© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 250
    Prev
    Next
    INDEX
    Explanations

    many followed by a noun

    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¸İä¼Ĺä¸įåIJĮ
    -0.28
    ä¸Ńæľī
    -0.26
    大èĩ´
    -0.26
    ä¸ĢèĪ¬æĺ¯
    -0.24
    éĢļ常æĺ¯
    -0.24
    æĶ¶åĪ°äºĨ
    -0.24
     generally
    -0.23
    æľīèĩªå·±çļĦ
    -0.23
     stamina
    -0.22
    éĹ´éļĶ
    -0.22
    POSITIVE LOGITS
    /all
    0.31
    çļĦå±ĢéĿ¢
    0.26
    agh
    0.25
    older
    0.24
    çĶļèĩ³æĺ¯
    0.24
    /current
    0.23
    oux
    0.23
     poorer
    0.23
     circumstances
    0.23
     cases
    0.23
    Activations Density 0.070%

    No Known Activations