© 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. 55670
    Prev
    Next
    INDEX
    Explanations

    provided for

    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
    åŁĤ
    -0.10
    ä»Ģä¹Īåij¢
    -0.10
    èĻı
    -0.10
    å«ģ
    -0.09
    ä»Ģä¹ĪæĦıæĢĿ
    -0.09
    èIJ¥ä¸ļé¢Ŀ
    -0.09
    èĥĽ
    -0.08
    fld
    -0.08
    cas
    -0.08
    èĥª
    -0.08
    POSITIVE LOGITS
     пÑĢедÑĥÑģ
    0.11
    ocre
    0.10
    æ´¾
    0.09
    鬣
    0.09
    æ´¾åĩº
    0.09
    atism
    0.09
    ä¼łè¯´
    0.09
    Signed
    0.09
    æ¶Į
    0.08
     TERMS
    0.08
    Activations Density 0.065%

    No Known Activations