© 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. 34860
    Prev
    Next
    INDEX
    Explanations

    trademarks, property, and rights

    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
    dden
    -0.09
    æĻĶ
    -0.09
    IOUS
    -0.08
    社ä¼ļåıijå±ķ
    -0.08
    ä¹ĭ声
    -0.08
    çļĦç¼ĺ
    -0.08
    å¾Ĥ
    -0.08
    acho
    -0.08
    ä½ıæĪ¿åĴĮ
    -0.08
    äºĭä¸ļåıijå±ķ
    -0.08
    POSITIVE LOGITS
    à¸ģว
    0.09
    ä¸įå®ī
    0.09
    mania
    0.09
    avis
    0.08
     Har
    0.08
    ÙĦØŃ
    0.08
    大纲
    0.08
    å¿ĥå¢ĥ
    0.08
    LERÄ°
    0.08
    uckland
    0.08
    Activations Density 0.054%

    No Known Activations