© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    Gloucester, Shield, Cross, autism

    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
    们
    -0.09
    éĺ´éĺ³
    -0.09
    åĿŀ
    -0.09
    ivil
    -0.09
    åģĮ
    -0.09
     обо
    -0.08
     interrupts
    -0.08
    å¢Ģ
    -0.08
    çłĮ
    -0.08
    åıįé¦Ī
    -0.08
    POSITIVE LOGITS
    unic
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    âĸ»
    0.09
    eler
    0.09
    代表
    0.09
    sworth
    0.09
    ayar
    0.09
    ä¸įéĻIJ
    0.09
    æĺ¶
    0.09
    ÑĥÑĩа
    0.09
    Activations Density 0.003%

    No Known Activations