© 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. 30862
    Prev
    Next
    INDEX
    Explanations

    gusts or puffy

    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
    è´¨
    -0.09
    骡
    -0.09
    ç¼Ģ
    -0.09
    jos
    -0.09
    åĿ¡
    -0.08
    åı¬å¼Ģ
    -0.08
     Heads
    -0.08
     reprint
    -0.08
    翻身
    -0.08
    QUAL
    -0.08
    POSITIVE LOGITS
    奢
    0.09
    ä»İ严
    0.09
    annis
    0.09
    ÑģÑĥ
    0.09
    çħī
    0.09
    亿ä¸ĩ
    0.09
    onical
    0.09
    ä»İ严治
    0.08
    鸢
    0.08
    /span
    0.08
    Activations Density 0.047%

    No Known Activations