© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    ranking or order

    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
    å®Ŀè´µçļĦ
    -0.10
    罡
    -0.10
    éļ¾å¿ĺ
    -0.10
    æĪIJ为ä¸ĢåIJį
    -0.09
    åħ¬çĽĬæĢ§
    -0.09
    ä¸įå¼Ģ
    -0.09
    èIJĿ
    -0.09
     hết
    -0.09
    å§ĵ
    -0.09
    Ùģات
    -0.09
    POSITIVE LOGITS
    upo
    0.10
    åĩłå®¶
    0.08
    ober
    0.08
     Bottom
    0.08
    Bottom
    0.08
    âĹĪ
    0.08
    بث
    0.08
    åĨł
    0.08
     Catch
    0.08
     Uri
    0.08
    Activations Density 0.013%

    No Known Activations