© 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. 39925
    Prev
    Next
    INDEX
    Explanations

    listing information

    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
    ç¯Ĩ
    -0.09
    é³ĸ
    -0.09
    款å¼ı
    -0.09
    ế
    -0.09
    åIJ»
    -0.09
     bumper
    -0.09
    æł·çļĦ
    -0.09
    æĨİ
    -0.08
    éªĦ
    -0.08
    æĤĴ
    -0.08
    POSITIVE LOGITS
    å®ŀåľ°
    0.10
    è¿Ļå¥Ĺ
    0.09
    çļĩåĨł
    0.09
    ä½İæĪIJæľ¬
    0.08
    æ´¾
    0.08
    éĩıåĮĸ
    0.08
    _overlay
    0.08
    çĢļ
    0.08
    æĤĦ
    0.08
    让æĤ¨
    0.08
    Activations Density 0.029%

    No Known Activations