© 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. 29392
    Prev
    Next
    INDEX
    Explanations

    station (STA), gang, carrier, film

    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
    tant
    -0.10
    atron
    -0.10
    oney
    -0.10
    å¢ĥçķĮ
    -0.09
    åĪ©äºļ
    -0.09
    裳
    -0.09
    没è§ģè¿ĩ
    -0.09
    -0.09
    ances
    -0.09
    sert
    -0.09
    POSITIVE LOGITS
    nement
    0.14
    ç«Ļéķ¿
    0.13
    arity
    0.12
    eros
    0.11
    ned
    0.10
    ero
    0.10
    à¹Ĥà¸Ĺร
    0.10
     меÑĤÑĢо
    0.10
    rud
    0.10
    aru
    0.10
    Activations Density 0.031%

    No Known Activations