© 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. 58029
    Prev
    Next
    INDEX
    Explanations

    Shanghai and Chinese place names

    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
    zos
    -0.09
    zÄħ
    -0.09
    zilla
    -0.09
    ç°
    -0.09
    igg
    -0.08
    ials
    -0.08
     Wars
    -0.08
     возможноÑģÑĤи
    -0.08
    çĺ´
    -0.08
     tÃł
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.11
    erton
    0.10
     edition
    0.09
     помоÑīÑĮ
    0.09
    æĿ²
    0.09
    åĮ»ç§ij大åѦ
    0.09
    çİ°æľī
    0.09
    REW
    0.09
     Edition
    0.08
    çĴĺ
    0.08
    Activations Density 0.024%

    No Known Activations