© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    providing quality or service

    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
    åĤ¢
    -0.10
    åĿŀ
    -0.10
    æIJŀ
    -0.09
    让ä»ĸ们
    -0.09
    ä¸Ģç¬ij
    -0.09
    è®ĵä»ĸåĢij
    -0.08
    _traffic
    -0.08
    èĢĦ
    -0.08
     IMPLEMENT
    -0.08
    è¶ĭåĬ¿
    -0.08
    POSITIVE LOGITS
    é«ĺè´¨éĩı
    0.11
    èĪĽ
    0.10
    é«ĺåĵģè´¨
    0.10
     каÑĩеÑģÑĤв
    0.09
    çļĦåIJĦ项
    0.09
     quality
    0.08
    åħ´å¥ĭ
    0.08
    aille
    0.08
     ÑĥÑģлÑĥги
    0.08
    åĪĨä¼ļ
    0.08
    Activations Density 0.049%

    No Known Activations