© 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. 10644
    Prev
    Next
    INDEX
    Explanations

    haworth, hall, palace

    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
    opot
    -0.10
    é¢
    -0.09
    TRA
    -0.09
     dụ
    -0.09
    ä¸ĭå·´
    -0.08
     Wes
    -0.08
    ç¿¡ç¿ł
    -0.08
    éķ¶
    -0.08
    澡
    -0.08
    agged
    -0.08
    POSITIVE LOGITS
    ille
    0.09
    ouse
    0.09
    croft
    0.09
    ä¸Ģæľ¬ä¹¦
    0.09
    eron
    0.09
    èĮ
    0.09
    èĭŁ
    0.08
    ean
    0.08
    ening
    0.08
    /or
    0.08
    Activations Density 0.006%

    No Known Activations