© 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. 24309
    Prev
    Next
    INDEX
    Explanations

    azerbaijani names and places

    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
    åĩºè·¯
    -0.11
    lessly
    -0.10
    ÑĥÑĩ
    -0.10
    ucht
    -0.10
    å±ij
    -0.09
    责任ç¼ĸè¾ij
    -0.09
     chc
    -0.09
    TextWriter
    -0.09
    ucks
    -0.09
    侬
    -0.09
    POSITIVE LOGITS
    istan
    0.11
    åĪ©äºļ
    0.09
    æĸ¯åĿ¦
    0.09
    ya
    0.09
    é¾ĥ
    0.08
    /Runtime
    0.08
    èĮ¨
    0.08
    istani
    0.08
    zerbai
    0.08
    éļ§
    0.08
    Activations Density 0.013%

    No Known Activations