© 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. 48481
    Prev
    Next
    INDEX
    Explanations

    beneficiaries of, profits through, responsibility 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
     Cle
    -0.10
    诣
    -0.10
    被éªĹ
    -0.09
    éģĺ
    -0.09
    entes
    -0.09
    æ¡¥æ¢ģ
    -0.09
    å·¥
    -0.09
    éªĩ
    -0.09
     pains
    -0.09
    å¹²åĩĢ
    -0.09
    POSITIVE LOGITS
    æĺİçŁ¥
    0.10
    享çĶ¨
    0.10
    æļĹæļĹ
    0.10
    责任
    0.09
    æľīæĿ¡ä»¶
    0.09
     responsibility
    0.09
     Responsibility
    0.09
    éļIJçŀĴ
    0.09
     knowingly
    0.09
     Peak
    0.09
    Activations Density 0.117%

    No Known Activations