© 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. 23829
    Prev
    Next
    INDEX
    Explanations

    watch movement mechanics

    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
    èĨº
    -0.11
    é¢Ĩè¢ĸ
    -0.09
    迹
    -0.09
    æ¶ĤæĸĻ
    -0.09
    æŃ£å¼ı
    -0.08
    追踪
    -0.08
    æģķ
    -0.08
    ://${
    -0.08
    _HEADERS
    -0.08
    _HIT
    -0.08
    POSITIVE LOGITS
    è´»
    0.09
    ä¼łåĬ¨
    0.09
     меÑħаниз
    0.08
    powered
    0.08
    bank
    0.08
     меÑħанизм
    0.08
    éªŀ
    0.08
     Steele
    0.08
    mill
    0.08
    丰å¯Įå¤ļ彩
    0.08
    Activations Density 0.093%

    No Known Activations