© 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. 4369
    Prev
    Next
    INDEX
    Explanations

    xhtml definition

    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
    æŃ£éĿ¢
    -0.10
    ä¸įå®Į
    -0.10
    ä¹ĭéĻħ
    -0.09
    ennes
    -0.08
    çŁ
    -0.08
    åıijçĶŁåľ¨
    -0.08
    æŶæĬ¥
    -0.08
    åijĪçİ°åĩº
    -0.08
     projected
    -0.08
     reim
    -0.08
    POSITIVE LOGITS
    ê°Ģìŀħ
    0.10
    åĬłåħ¥
    0.10
    庸
    0.09
    æľ¬ç«Ļ
    0.09
    æļĹæļĹ
    0.09
    çļĦä¸Ģåijĺ
    0.09
    åIJĥå¾Ĺ
    0.09
    æѤåīį
    0.09
    Raised
    0.09
    è¿Ļä¹Īä¹ħ
    0.09
    Activations Density 0.046%

    No Known Activations