© 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. 57791
    Prev
    Next
    INDEX
    Explanations

    sharing emails with others

    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
    å¹²äºĭ
    -0.08
    èį¨
    -0.08
     Kendall
    -0.08
    æĻļå¹´
    -0.07
    头æĿ¡
    -0.07
     himself
    -0.07
    ä¸į容æĺĵ
    -0.07
    webdriver
    -0.07
    ators
    -0.07
     themselves
    -0.07
    POSITIVE LOGITS
    åĪ«çļĦ
    0.10
    ç»ĻäºĨ
    0.10
    åħļç»Ħç»ĩ
    0.10
    åħ¶ä»ĸ
    0.10
    äºĨä¸Ģ个
    0.09
    æĽľ
    0.09
    åħ¶ä»ĸ人
    0.09
     дÑĢÑĥгие
    0.09
    _named
    0.09
    äºĨä¸Ģ
    0.09
    Activations Density 0.019%

    No Known Activations