© 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. 35411
    Prev
    Next
    INDEX
    Explanations

    defense and protection

    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
    夸
    -0.12
    ç«Ļéķ¿
    -0.10
    sher
    -0.09
    кÑĢа
    -0.09
    æīĵçł´
    -0.09
    河水
    -0.09
    åĿļæĮģä¸įæĩĪ
    -0.09
     multit
    -0.09
    èħĶ
    -0.09
    ä¸įå¾Ĺä¸į说
    -0.08
    POSITIVE LOGITS
    æľŁåĨħ
    0.12
    æݪæĸ½
    0.10
    ãĤ¹ãĤ¯
    0.09
     against
    0.09
    against
    0.09
    æIJŀå¾Ĺ
    0.09
    åľ£åľ°
    0.09
    大éŨ
    0.08
    设æĸ½å»ºè®¾
    0.08
     anticipating
    0.08
    Activations Density 0.064%

    No Known Activations