© 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. 11637
    Prev
    Next
    INDEX
    Explanations

    discussing and attending meetings

    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
    Posting
    -0.22
    çī¹èī²ç¤¾ä¼ļ
    -0.22
    éĺŁåijĺ
    -0.21
    管çIJĨæĿ¡ä¾ĭ
    -0.21
    schema
    -0.21
    chooser
    -0.20
    ä»»ä½ķæŶåĢĻ
    -0.20
    æĪij们çİ°åľ¨
    -0.19
    æĶ»åĿļæĪĺ
    -0.19
    åľĺéļĬ
    -0.19
    POSITIVE LOGITS
    çłĶ讨
    0.33
    交æµģ
    0.32
    讨论
    0.32
    æݢ讨
    0.31
     discussions
    0.31
     discussion
    0.30
     discuss
    0.27
    yme
    0.26
     discussing
    0.26
     discusses
    0.24
    Activations Density 0.069%

    No Known Activations