© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7666
    Prev
    Next
    INDEX
    Explanations

    award recognition

    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
    åĩıå¼±
    -0.09
     ба
    -0.09
    æ´¾
    -0.09
    dba
    -0.08
    rites
    -0.08
    çķĻä¸ĭäºĨ
    -0.08
    ç»Ŀ大éĥ¨åĪĨ
    -0.08
    èIJ½åΰå®ŀ
    -0.08
    bite
    -0.08
    è¿Ļåĩł
    -0.08
    POSITIVE LOGITS
     Hastings
    0.10
    年以ä¸Ĭ
    0.09
    åħ·æľīèī¯å¥½
    0.09
    å½·
    0.09
    年度
    0.09
    åħ¸èĮĥ
    0.09
     outstanding
    0.09
     лÑĥÑĩ
    0.09
    æ£ĭçīĮ
    0.08
    ypy
    0.08
    Activations Density 0.052%

    No Known Activations