© 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. 23352
    Prev
    Next
    INDEX
    Explanations

    World War I

    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
    解æĶ¾åĨĽ
    -0.10
    第ä¸ī代
    -0.09
    é¢Ĩè·ij
    -0.09
    ä¸ī代
    -0.09
     deb
    -0.08
    ota
    -0.08
    éĤ£ä»½
    -0.08
    ä¸įéĶĪ
    -0.08
    æ··åIJĪ
    -0.08
    åĵģä½į
    -0.08
    POSITIVE LOGITS
    (JS
    0.10
    ewan
    0.10
    åįģäºĮæĿ¡
    0.09
    磶
    0.09
    Allen
    0.09
    alking
    0.09
    çģ«è½¦ç«Ļ
    0.08
    ller
    0.08
    常å·ŀ
    0.08
    fos
    0.08
    Activations Density 0.185%

    No Known Activations