© 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. 33513
    Prev
    Next
    INDEX
    Explanations

    interface interactions and navigation

    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
    ascript
    -0.10
    _INTERRUPT
    -0.09
    æĪ´
    -0.08
    Posting
    -0.08
    éķ¿å¤§äºĨ
    -0.08
    读åIJİ
    -0.08
    ign
    -0.08
    æ¯ĭ
    -0.08
     Blogs
    -0.08
    Span
    -0.07
    POSITIVE LOGITS
    åĽ¾å½¢
    0.10
    ç½¢äºĨ
    0.09
    ç¼ĸè¾ij
    0.09
    ç»´å¥ĩ
    0.09
    ä¸ĺ
    0.09
    çļĦç»ıåħ¸
    0.09
     wizards
    0.09
    çĪ±åĽ½ä¸»ä¹ī
    0.09
    ä¼Ĭæĭī
    0.09
    .edit
    0.09
    Activations Density 0.376%

    No Known Activations