© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    U.S. followed by Army, Pat, Supreme

    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
    annies
    -0.10
    æĸ¹éĿ¢çļĦ
    -0.09
    ippines
    -0.09
    夫å¦ĩ
    -0.09
    roc
    -0.09
    é£ŀè·ĥ
    -0.09
    éļĭ
    -0.09
    oretical
    -0.09
    imonials
    -0.09
    ä¸įä»ħè¦ģ
    -0.09
    POSITIVE LOGITS
    å¾Ģ
    0.09
    æīĢæľīçļĦ
    0.08
    ober
    0.08
    lef
    0.08
    èĽ°
    0.08
    еÑģÑĤво
    0.08
    oba
    0.08
     Headquarters
    0.08
    æ°¨åŁº
    0.07
    /plugin
    0.07
    Activations Density 0.305%

    No Known Activations