© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21455
    Prev
    Next
    INDEX
    Explanations

    pirates or pirate

    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
    å¿¡
    -0.12
    Ùij
    -0.11
    argo
    -0.09
    ses
    -0.09
    ington
    -0.09
    ément
    -0.09
    most
    -0.09
     Äijỡ
    -0.08
    ded
    -0.08
    lam
    -0.08
    POSITIVE LOGITS
    ãģĦãģªãģĦ
    0.10
    ë¡Ń
    0.10
    obao
    0.10
    åħ¬ç«ł
    0.10
    zsche
    0.09
    èīĩ
    0.09
    æĻ¨æĬ¥
    0.09
    SEA
    0.09
    æł·çļĦ
    0.09
    нем
    0.08
    Activations Density 0.005%

    No Known Activations