© 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. 18762
    Prev
    Next
    INDEX
    Explanations

    examples followed by parentheticals

    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
    ç»Ļä»ĸ们
    -0.09
    æ·¡å®ļ
    -0.09
    åĭĻ
    -0.09
    æĻļé¥Ń
    -0.09
    ãģłãģ£ãģŁãģ®ãģ§
    -0.09
    ç¨
    -0.09
    好çľĭ
    -0.08
    没æľīåĬŀæ³ķ
    -0.08
    å¼ĢåĬŀ
    -0.08
    åĬŀ
    -0.08
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.09
    åīįä¸įä¹ħ
    0.08
     nef
    0.08
    ksen
    0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    0.08
    æŁIJäºĽ
    0.08
    throat
    0.08
    ä¾ĭå¦Ĥ
    0.08
    追
    0.08
    åij¼
    0.08
    Activations Density 0.078%

    No Known Activations