© 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. 53464
    Prev
    Next
    INDEX
    Explanations

    passive, unconscious, implicit

    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
    éĿŀåĩ¡
    -0.10
    社ä¼ļåĮĸ
    -0.09
    unker
    -0.09
    åĬ«
    -0.09
    ä¸įä¸Ģæł·
    -0.08
    aph
    -0.08
    æĿ¯
    -0.08
    ä¸įä¸Ģæł·çļĦ
    -0.08
    uent
    -0.08
    æŶä¸į
    -0.08
    POSITIVE LOGITS
    mente
    0.11
    ware
    0.10
    ãģ¾ãģ¾
    0.10
    istan
    0.10
    ities
    0.10
    ä¼ı
    0.09
    京津åĨĢ
    0.09
    wares
    0.09
    -most
    0.09
    大家ä¸Ģèµ·
    0.09
    Activations Density 0.216%

    No Known Activations