© 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. 30391
    Prev
    Next
    INDEX
    Explanations

    a, the, any, those, to

    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
     own
    -0.10
    æīĵä»Ĺ
    -0.08
    Own
    -0.08
    åĴ¨è¯¢æľįåĬ¡
    -0.08
    æ¶Īè´¹èĢħçļĦ
    -0.08
    arer
    -0.08
    ä»ĸ们æĺ¯
    -0.08
    _placement
    -0.07
    ITS
    -0.07
    ä¸ĩåIJį
    -0.07
    POSITIVE LOGITS
     ones
    0.16
    ä½ľåĵģ
    0.13
    éĤ£ç§į
    0.12
     Ones
    0.11
    ãĤĤãģ®ãģĮ
    0.11
    ones
    0.10
    çļĦå°±æĺ¯
    0.10
    çļĦä½ľåĵģ
    0.10
    ä¸ľè¥¿
    0.10
    家ä¼Ļ
    0.10
    Activations Density 0.732%

    No Known Activations