© 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. 58673
    Prev
    Next
    INDEX
    Explanations

    don't miss it

    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
    ä¸įæŃ»
    -0.10
    å¾Ī强
    -0.10
    奢
    -0.09
    å¾Īæ·±
    -0.09
    èĭ±æł¼
    -0.09
    å¾Īé«ĺ
    -0.09
    ä¸į满
    -0.09
    èļ©
    -0.09
    å¾Īåĸľæ¬¢
    -0.09
    ä¸įä¿¡
    -0.08
    POSITIVE LOGITS
    æľºä¼ļ
    0.10
     next
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
     Becker
    0.08
     Stub
    0.08
    çľ¼åīįçļĦ
    0.08
     opportunity
    0.08
    ä¸ĭ次
    0.08
    ÑĨеп
    0.08
    è¿Ļæł·ä¸Ģ个
    0.08
    Activations Density 0.007%

    No Known Activations