© 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. 5752
    Prev
    Next
    INDEX
    Explanations

    name, fame, recognition, reputation

    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
    ç²¾
    -0.09
    oll
    -0.09
     spawn
    -0.09
    éĶģå®ļ
    -0.08
    çİĭèĢħ
    -0.08
    orie
    -0.08
    landers
    -0.08
    å¥ı
    -0.08
    è¿ĩå¤ļ
    -0.08
    æĪij们çİ°åľ¨
    -0.08
    POSITIVE LOGITS
    京åŁİ
    0.09
    éĹº
    0.09
    为主é¢ĺçļĦ
    0.09
    é«ĺ楼
    0.09
     Fet
    0.08
    çŁŃæŶéĹ´åĨħ
    0.08
    跻身
    0.08
    æł¹åŁº
    0.08
    ihar
    0.08
    æĸ°æĪ¿
    0.08
    Activations Density 0.045%

    No Known Activations