© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3565
    Prev
    Next
    INDEX
    Explanations

    hand gestures and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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¸ĢåĪ»
    -0.11
    mall
    -0.09
    ç½ijåıĭè¯Ħ论
    -0.09
    ussia
    -0.08
    èĢ½
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
     Het
    -0.08
    Ặ
    -0.08
    好人
    -0.08
    panion
    -0.08
    POSITIVE LOGITS
    æįº
    0.12
    ä¸Ģä¸ĭ
    0.11
    æĮ¥æīĭ
    0.11
     ÑĢÑĥк
    0.10
    羨
    0.10
    æijĩ
    0.10
    æĹĹä¸ĭ
    0.10
    é¼łæłĩ
    0.10
    èĢ¸
    0.09
    计åĪĴ
    0.09
    Activations Density 0.063%

    No Known Activations