© 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. 26191
    Prev
    Next
    INDEX
    Explanations

    in all likelihood

    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
    æŁIJ个
    -0.09
    tom
    -0.08
    les
    -0.08
    PEC
    -0.08
    pek
    -0.08
     Programme
    -0.08
    æĿ¥çļĦ
    -0.08
    ÑĥÑīе
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
     Justin
    -0.07
    POSITIVE LOGITS
     ÑĢÑĥков
    0.09
    æ³ł
    0.09
    æ³
    0.09
    .literal
    0.09
    onet
    0.08
    æ¡ij
    0.08
    åĬ¡
    0.08
     Dre
    0.08
    olicy
    0.08
    :description
    0.08
    Activations Density 0.025%

    No Known Activations