© 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. 49474
    Prev
    Next
    INDEX
    Explanations

    greater part of

    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
    æ´¾
    -0.10
    å°ıå°ı
    -0.10
    anas
    -0.10
    pyx
    -0.10
    UCT
    -0.09
    æĺİæĹ¥
    -0.09
    PILE
    -0.09
    _soc
    -0.09
    ysz
    -0.09
     YYSTACK
    -0.09
    POSITIVE LOGITS
    æķ´ä¸ª
    0.19
     entire
    0.19
     entirety
    0.17
    大éĥ¨åĪĨ
    0.16
    æķ´åĢĭ
    0.16
    æķ´ä¸ªäºº
    0.16
    åħ¨ç¨ĭ
    0.15
    ç»Ŀ大éĥ¨åĪĨ
    0.15
    ç»Ŀ大å¤ļæķ°
    0.14
     веÑģÑĮ
    0.14
    Activations Density 0.208%

    No Known Activations