© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    here in geographic locations

    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
    大纲
    -0.10
    以èī²
    -0.09
    æķ´ä¸ª
    -0.09
    èµĽåIJİ
    -0.08
    毫ä¸įçĬ¹è±«
    -0.08
    èµ°è¿ij
    -0.08
    ä¾®
    -0.08
    æĪIJéķ¿
    -0.08
    mere
    -0.08
    éĢĨè¡Į
    -0.08
    POSITIVE LOGITS
    undy
    0.10
    ç²¾
    0.09
    常说
    0.08
    æݨ广åºĶçĶ¨
    0.08
    acket
    0.08
    æݨ广
    0.08
    主è¦ģçĶ¨äºİ
    0.08
    å·²æĺ¯
    0.08
    isc
    0.08
    onical
    0.07
    Activations Density 0.021%

    No Known Activations