© 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. 47548
    Prev
    Next
    INDEX
    Explanations

    language, common protocol, speak english

    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
     Goldberg
    -0.09
    LineNumber
    -0.09
    衬
    -0.08
    achi
    -0.08
    panion
    -0.08
    æģ¸
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    帽
    -0.08
    社ä¼ļ责任
    -0.08
    _lex
    -0.08
    POSITIVE LOGITS
    è¯Ńè¨Ģ
    0.18
    çļĦè¯Ńè¨Ģ
    0.17
     language
    0.17
    language
    0.15
    /language
    0.15
     ÑıзÑĭк
    0.15
    èªŀè¨Ģ
    0.15
     languages
    0.14
    .language
    0.14
    (language
    0.14
    Activations Density 0.114%

    No Known Activations