© 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. 38856
    Prev
    Next
    INDEX
    Explanations

    consumer rights and regulations

    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
    人äºĭ
    -0.10
    åIJİå¤ĩ
    -0.09
    ä¿Ŀ管
    -0.09
    gren
    -0.08
    веÑĤ
    -0.08
    çīĿ
    -0.08
    ç¿°
    -0.08
    åĢĻ
    -0.08
    åĮĻ
    -0.08
    仪
    -0.08
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.14
    æ¶Īè´¹èĢħ
    0.13
    éªļæī°
    0.13
     Consumer
    0.13
     consumer
    0.12
    Consumer
    0.12
    æ¶Īè²»èĢħ
    0.12
    .consumer
    0.11
     consumers
    0.11
    _consumer
    0.11
    Activations Density 0.038%

    No Known Activations