© 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. 56034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    pedia
    -0.10
    溱
    -0.10
    rut
    -0.09
     cruise
    -0.09
    stim
    -0.09
    izen
    -0.09
    é¢Ī
    -0.08
    itech
    -0.08
    é¼İ
    -0.08
    èĪªè¿IJ
    -0.08
    POSITIVE LOGITS
    pressive
    0.09
    apy
    0.09
    çªij
    0.08
    æĻļé¥Ń
    0.08
    ä¸įç»ı
    0.08
    anian
    0.08
    主ä¹īæĢĿæĥ³
    0.08
    ÙĬات
    0.08
    athe
    0.07
    (QL
    0.07
    Activations Density 0.087%

    No Known Activations