© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54524
    Prev
    Next
    INDEX
    Explanations

    sentence entered

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¥éŨ
    -0.10
    大éĿ¢ç§¯
    -0.10
    åĮ¡
    -0.09
    åĽĽå·Ŀçľģ
    -0.09
    åĽĽå·Ŀ
    -0.09
    å®ĭ
    -0.09
    leep
    -0.09
    æĿŀ
    -0.09
    åĽłä¸ºå®ĥ
    -0.09
    æģŃ
    -0.08
    POSITIVE LOGITS
    究
    0.10
    ÙĬÙĪÙĨ
    0.10
    Monad
    0.09
    angel
    0.09
     Luz
    0.08
    pen
    0.08
     ê±´
    0.08
    slt
    0.08
     mural
    0.08
    .Ed
    0.08
    Activations Density 0.370%

    No Known Activations