© 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. 18902
    Prev
    Next
    INDEX
    Explanations

    by improve

    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
    秩
    -0.08
    èĸ¨
    -0.08
    ihan
    -0.08
    ç»ıè¿ĩå¤ļå¹´
    -0.08
    æ¯ı个人éĥ½
    -0.08
     wedge
    -0.08
    ä¼ļåijĺ
    -0.08
    dated
    -0.08
    åŁĥå°Ķ
    -0.08
    æĹ¥æľŁ
    -0.08
    POSITIVE LOGITS
    æħķ
    0.10
    룴
    0.10
    豫
    0.09
    æħ·æħ¨
    0.09
    æł·åŃIJ
    0.09
    窥
    0.08
     Sanctuary
    0.08
    é»ĺ
    0.08
    .heroku
    0.08
    æijĦ
    0.08
    Activations Density 0.001%

    No Known Activations