© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52001
    Prev
    Next
    INDEX
    Explanations

    India

    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
    DAQ
    -0.09
    侯
    -0.09
    ight
    -0.09
    mes
    -0.09
    ropy
    -0.09
    è¿ľæĸ¹
    -0.09
    rib
    -0.09
    tra
    -0.08
    ibbon
    -0.08
    åĬ¨äºº
    -0.08
    POSITIVE LOGITS
    apolis
    0.12
    سة
    0.10
    zelf
    0.09
    hana
    0.09
    ustrial
    0.09
    -European
    0.09
    -Israel
    0.09
     nghá»ģ
    0.08
    OrNull
    0.08
    uction
    0.08
    Activations Density 0.049%

    No Known Activations