© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36478
    Prev
    Next
    INDEX
    Explanations

    spokesperson, editor, manager, secretary

    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
    æĭŁ
    -0.09
    æī§æ³ķ人åijĺ
    -0.09
    æ¶Īè²»èĢħ
    -0.09
    åĪĽå§ĭ人
    -0.09
    女ç¥ŀ
    -0.09
    èĵĭ
    -0.09
    apt
    -0.08
    纯
    -0.08
    æ¶Īè´¹èĢħ
    -0.08
     Lid
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.13
    åĬ©çIJĨ
    0.10
    ä½İä½į
    0.10
    éª
    0.10
    缺å¸Ń
    0.09
    è´Łè´£
    0.09
    겸
    0.09
    åħį责声æĺİ
    0.09
    виÑģ
    0.09
    ä¸įè¡Į
    0.09
    Activations Density 0.267%

    No Known Activations