© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    potential future roles

    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»»ä½ķ人
    -0.10
     Fres
    -0.09
    Ñħа
    -0.08
    é»İæĺİ
    -0.08
    иÑģк
    -0.08
    渡
    -0.08
    æľīè¿ĩ
    -0.08
     Owned
    -0.08
    ủng
    -0.08
    ãģ¡ãĤī
    -0.08
    POSITIVE LOGITS
    çİĭèĢħ
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.09
    åijĬè¯īä»ĸ
    0.09
    å·²ä¹ħçļĦ
    0.09
    å¤©åºľ
    0.09
    æŀĦ
    0.09
    æĤłæĤł
    0.09
    ä¸Ŀä¸Ŀ
    0.09
    Ki
    0.09
    ä¹ĭåĬ¿
    0.09
    Activations Density 0.264%

    No Known Activations