© 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. 26673
    Prev
    Next
    INDEX
    Explanations

    league title, play, or wide

    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
    æŶåħī
    -0.11
    ç«Ļéķ¿
    -0.10
    æĹ¶è¾°
    -0.09
    éĩį伤
    -0.09
     lá»Ńa
    -0.09
    æ²¹èħ»
    -0.09
    è´¼
    -0.09
    åĸľçĪ±
    -0.09
    æłijåı¶
    -0.09
    äºĨ好å¤ļ
    -0.09
    POSITIVE LOGITS
    -wide
    0.10
    èĮĥåĽ´åĨħ
    0.08
     пÑĢаво
    0.08
    ики
    0.08
    ihan
    0.08
    å·¥ä½ľèĢħ
    0.08
    碾
    0.08
    åĨħçļĦ
    0.08
    wide
    0.08
    ste
    0.08
    Activations Density 0.013%

    No Known Activations