© 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. 29838
    Prev
    Next
    INDEX
    Explanations

    Playing with dolls and games

    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
    eneg
    -0.11
    iad
    -0.10
    åĪĨå±Ģ
    -0.10
    ä¸Ģ群人
    -0.09
     ÑģÑĤÑĥд
    -0.09
    缴åįĩæľº
    -0.09
     Barker
    -0.09
    æĢİæł·
    -0.09
    crow
    -0.09
    å±Ģ
    -0.09
    POSITIVE LOGITS
    çİ©èĢį
    0.13
    çİ©åħ·
    0.12
    æĵĴ
    0.09
    ÑĢай
    0.09
     doll
    0.09
    çļĦ游æĪı
    0.09
     play
    0.09
     dolls
    0.09
    ä¸Ńåħ³
    0.08
    åĵĦ
    0.08
    Activations Density 0.090%

    No Known Activations