© 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. 32240
    Prev
    Next
    INDEX
    Explanations

    stent graft and radial sealing

    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
    åīĥ
    -0.09
    hea
    -0.08
    .Ret
    -0.08
    帮å¿Ļ
    -0.08
    switch
    -0.08
    aryl
    -0.08
    tti
    -0.08
    ç²¹
    -0.08
     Cer
    -0.08
    dale
    -0.08
    POSITIVE LOGITS
    æ³ķåħ°
    0.10
    沿线
    0.10
    段
    0.09
    åħ¨æĸ°çļĦ
    0.09
    åŃIJåŃĻ
    0.09
    åĪ¸
    0.09
    Pipeline
    0.09
    滩
    0.08
     Aviv
    0.08
    rib
    0.08
    Activations Density 0.304%

    No Known Activations