© 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. 31478
    Prev
    Next
    INDEX
    Explanations

    change his name or things

    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
    ä¸įåĩº
    -0.10
    oping
    -0.09
     geg
    -0.09
    åŁºç¡Ģä¸Ĭ
    -0.09
    ä¸įæĺİ
    -0.08
    åĨĴ
    -0.08
    ëŀĮ
    -0.08
    venge
    -0.08
    åİŁæĿ¥æĺ¯
    -0.08
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    -0.08
    POSITIVE LOGITS
    æĪª
    0.10
    èĤ¤
    0.10
    developer
    0.09
    人éĹ´
    0.09
    æį¢ä¸ª
    0.09
    è¯įæĿ¡
    0.08
    holm
    0.08
    à¹ģà¸Ľà¸¥
    0.08
    涧
    0.08
    çĻ½é©¬
    0.08
    Activations Density 0.043%

    No Known Activations