© 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. 57901
    Prev
    Next
    INDEX
    Explanations

    Ingenuity, Lincoln, Smith

    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
    _sink
    -0.09
    å´´
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    å®ĮåĸĦ
    -0.08
    鲤
    -0.08
    仲
    -0.08
    秧
    -0.08
    ems
    -0.08
    æī¼
    -0.08
    merged
    -0.08
    POSITIVE LOGITS
    åĬ¨äºº
    0.10
    ÑĢа
    0.10
    好å¥ĩ
    0.10
    主è¦ģåĨħ容
    0.10
    éļĥ
    0.09
    æĭĽåij¼
    0.09
     rover
    0.09
    æĢ»éĺŁ
    0.09
    è´±
    0.09
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    Activations Density 0.177%

    No Known Activations