© 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. 50171
    Prev
    Next
    INDEX
    Explanations

    evaluated, converts, causes, highlights

    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
    è¿Ļç±»
    -0.08
    ãģĦãģĭ
    -0.08
    ä»ħä»ħæĺ¯
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    ãģĦãģij
    -0.08
     neither
    -0.08
     this
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ä¸įä»ħè¦ģ
    -0.08
    èħ°éĥ¨
    -0.08
    POSITIVE LOGITS
    togroup
    0.11
    ÑĪи
    0.10
    RYPT
    0.10
    âĺ¾
    0.09
     ìĿ¼ë¶Ģ
    0.09
     governed
    0.09
     ÄIJến
    0.09
    LETE
    0.09
     Sapphire
    0.08
    /styles
    0.08
    Activations Density 0.249%

    No Known Activations