© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    simulation, exercise, training

    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
    趴
    -0.10
    èĨ³
    -0.10
    çħ§
    -0.09
    æĹłæĦı
    -0.09
    åįĩåѦ
    -0.08
    ä¸¥æł¼æī§è¡Į
    -0.08
    ç½¢
    -0.08
    é¢Ĩè·ij
    -0.08
    attended
    -0.08
    æĻĵ
    -0.08
    POSITIVE LOGITS
    模æĭŁ
    0.14
    æ¡Īä¾ĭ
    0.12
    å®ŀä¹ł
    0.12
    å®ŀè®Ń
    0.12
    ä»¿çľŁ
    0.12
    æ£ĺ
    0.11
     simulation
    0.11
    é²ľæ´»
    0.10
     Simulation
    0.10
    æĶ¹éĿ©
    0.10
    Activations Density 0.059%

    No Known Activations