© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21454
    Prev
    Next
    INDEX
    Explanations

    Apple Dictionary

    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
    æĸĩç«łæĿ¥æºIJ
    -0.09
    第ä¸Ģ个
    -0.09
    绫
    -0.09
    讫
    -0.09
    ساÙħ
    -0.08
    olem
    -0.08
    å°ıåŀĭ
    -0.08
    çĶļ
    -0.08
    å®ŀåĬĽ
    -0.08
    馥
    -0.08
    POSITIVE LOGITS
    éĢģæĿ¥
    0.08
    (getClass
    0.07
    éªĤ
    0.07
    ego
    0.07
    éľı
    0.07
    çľ¼çľĭ
    0.07
    haft
    0.07
    tics
    0.07
    æĶ¾ç¼ĵ
    0.07
    æĹıèĩªæ²»å·ŀ
    0.07
    Activations Density 2.292%

    No Known Activations