© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15175
    Prev
    Next
    INDEX
    Explanations

    hand actions and related phrases

    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
    äººæł¼
    -0.19
    èĦijåŃIJéĩĮ
    -0.18
    èĢĢçľ¼
    -0.17
    人çĶŁçļĦ
    -0.17
    æ¯ıä¸Ģ天
    -0.17
    ä»ĸèĩªå·±
    -0.17
    æķŀ
    -0.17
    个ä½ĵ
    -0.16
    ovation
    -0.16
    æĦıä¹īä¸Ĭ
    -0.16
    POSITIVE LOGITS
     hands
    0.25
    ðŁı»
    0.25
    -held
    0.24
    æı¡
    0.23
    hands
    0.23
    shake
    0.23
     Hands
    0.22
    缸åĬ©
    0.22
    /thumb
    0.22
     ÑĢÑĥк
    0.21
    Activations Density 0.032%

    No Known Activations