© 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. 18325
    Prev
    Next
    INDEX
    Explanations

    attitudes and theories of mind

    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
    ç¬ĶèĢħ
    -0.10
    åľ¨æł¡
    -0.09
    为æĤ¨
    -0.09
    ÑģÑĤÑĢел
    -0.09
    寸
    -0.08
    å°ıç¼ĸ
    -0.08
    æµģæĺŁ
    -0.08
    va
    -0.08
    åİŁåĽłä¹ĭä¸Ģ
    -0.08
    æİĮ声
    -0.08
    POSITIVE LOGITS
    ä»ĸ认为
    0.10
    åľ¨ä»ĸçļĦ
    0.09
    ako
    0.09
    izia
    0.09
     cre
    0.09
    娶
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
     Brom
    0.08
    ä¾į
    0.08
     supposedly
    0.08
    Activations Density 0.136%

    No Known Activations