© 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. 49938
    Prev
    Next
    INDEX
    Explanations

    revolt and revolution

    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
    éĿ¢æĿ¿
    -0.10
    ç¼ķ
    -0.10
    ç²¾ç»Ĩ
    -0.10
    åĮ£
    -0.10
    SSIP
    -0.09
    磫
    -0.09
    åĨ·åĨ·
    -0.09
    Svc
    -0.08
     bulletin
    -0.08
    Classic
    -0.08
    POSITIVE LOGITS
    éĿ©åij½
    0.11
     Occupy
    0.10
    é¢ľèī²
    0.09
    åIJĥå®Į
    0.09
    æĬĽå¼ĥ
    0.09
    HD
    0.09
     revolt
    0.08
    ç¾İå¦Ļ
    0.08
     HD
    0.08
    æĬĹè®®
    0.08
    Activations Density 0.165%

    No Known Activations