© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26120
    Prev
    Next
    INDEX
    Explanations

    existence and ontology

    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
    Negative Logits
    磫
    -0.10
    好åIJ§
    -0.10
    平淡
    -0.09
    éĵºè®¾
    -0.09
    åĿĬ
    -0.09
    æīĵçĮİ
    -0.08
    ç¨Ģ
    -0.08
    ãģ§ãģĻãģĹ
    -0.08
    åĪĽä¸ļ
    -0.08
     IDX
    -0.08
    POSITIVE LOGITS
    å®ŀä½ĵ
    0.12
     entities
    0.10
     entity
    0.10
    鬲
    0.10
     entityType
    0.10
    existent
    0.09
    åIJIJ
    0.09
    entities
    0.09
    åŁºæľ¬éĿ¢
    0.09
     existence
    0.09
    Activations Density 0.037%

    No Known Activations