© 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. 62053
    Prev
    Next
    INDEX
    Explanations

    æľīæĥ³è¦ģä¹°

    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
    顾èĻij
    -0.10
    enberg
    -0.09
    åĿ¦
    -0.08
    éŃģ
    -0.08
    è¥Ł
    -0.08
    NECT
    -0.08
    bat
    -0.08
    æķ´è½¦
    -0.08
    бÑĢи
    -0.08
    ả
    -0.08
    POSITIVE LOGITS
     simulated
    0.11
    模æĭŁ
    0.10
    æııåĨĻ
    0.10
    èĻļæŀĦ
    0.10
    çİ°å®ŀä¸Ń
    0.10
    ä»¿çľŁ
    0.10
    åī¯
    0.10
    æ¯Ķåĸ»
    0.10
    éªĩ
    0.09
    åŃĹæł·
    0.09
    Activations Density 0.674%

    No Known Activations