© 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. 27252
    Prev
    Next
    INDEX
    Explanations

    soap opera or SOAP API

    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»Ģä¹Īåij¢
    -0.10
    åĭĥåĭĥ
    -0.09
    èŀºä¸Ŀ
    -0.09
    -purpose
    -0.09
    åŃIJéĩĮ
    -0.09
    ãģ¾ãģĻãģĮ
    -0.09
    ocard
    -0.09
    åıªä¸º
    -0.09
    æĮ
    -0.09
     Bulls
    -0.09
    POSITIVE LOGITS
    ify
    0.11
    pery
    0.10
    æł·çļĦ
    0.10
    ги
    0.09
    licity
    0.09
    ification
    0.09
    gae
    0.09
    çŃı
    0.09
    ×ķ×ĺ
    0.09
     Conrad
    0.09
    Activations Density 0.007%

    No Known Activations