© 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. 30689
    Prev
    Next
    INDEX
    Explanations

    eating healthy food

    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
    åķ¤
    -0.09
     Stevens
    -0.09
    åĨįåĪ°
    -0.09
    ä¸Ģåı¥
    -0.09
    æĶ¶æ¬¾
    -0.08
     usage
    -0.08
    Usage
    -0.08
     Van
    -0.08
    erre
    -0.08
    管å±Ģ
    -0.08
    POSITIVE LOGITS
     пÑĢедоÑģÑĤавлен
    0.14
    æİīäºĨ
    0.10
    OffsetTable
    0.10
    åľ¨ä»Ĭå¹´
    0.10
    饱
    0.10
    ê°IJ
    0.10
    åIJŀ
    0.09
    æĿĤ
    0.09
    åĪ«äººçļĦ
    0.09
     tá»Ń
    0.09
    Activations Density 0.049%

    No Known Activations