© 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. 9737
    Prev
    Next
    INDEX
    Explanations

    Jain, Catholic, Yezidis, Christians, Catharism

    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
    æĭ¿æĿ¥
    -0.09
     Jamal
    -0.08
     poker
    -0.08
    /tab
    -0.08
     ench
    -0.08
    éĩįè¦ģåİŁåĽł
    -0.08
    ume
    -0.08
    .jupiter
    -0.08
     tripod
    -0.08
    çļ±
    -0.08
    POSITIVE LOGITS
    inan
    0.12
    åĵ¦
    0.10
    essim
    0.10
    åŀ«
    0.10
    åĭī
    0.09
    å·´å·´
    0.09
    èĽ®
    0.09
     sắc
    0.08
    æĦī
    0.08
    å¼Ģå·¥
    0.08
    Activations Density 0.022%

    No Known Activations