© 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. 26725
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    æīĢæľī人
    -0.09
    ç¼Ń
    -0.09
    æ©IJ
    -0.09
    è¿Ļæĺ¯ä¸Ģç§į
    -0.09
    çIJĨ解åĴĮ
    -0.08
    åĴĮ个人
    -0.08
    å¤§éĽ¨
    -0.08
    管çIJĨåĴĮ
    -0.08
    _inst
    -0.08
    大éŨ
    -0.08
    POSITIVE LOGITS
    ilio
    0.08
    ä¹Łå¥½
    0.08
    ãģ¤ãģį
    0.08
    è´¸æĺĵ
    0.08
    ä½³
    0.08
    æ¡©
    0.08
    ãģĬãģĿ
    0.07
    èµŀèµı
    0.07
    تا
    0.07
    æŀģ
    0.07
    Activations Density 0.338%

    No Known Activations