© 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. 63256
    Prev
    Next
    INDEX
    Explanations

    for

    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
    iolet
    -0.10
    æĹ©
    -0.10
    atsby
    -0.09
    èѦ
    -0.09
    даÑĢ
    -0.09
    åı¤ä»Ĭ
    -0.09
    峤
    -0.09
    odel
    -0.09
    身影
    -0.08
    ạp
    -0.08
    POSITIVE LOGITS
    ç³Ĭ
    0.09
    å¸ĪèµĦ
    0.08
    é»į
    0.08
    åIJĮæł·æĺ¯
    0.08
     squeeze
    0.08
    loff
    0.08
    vu
    0.08
    大ä¼Ĺ
    0.08
     Reed
    0.08
    ront
    0.08
    Activations Density 0.100%

    No Known Activations