© 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. 62064
    Prev
    Next
    INDEX
    Explanations

    versions and dates

    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
    äºĮèĥİ
    -0.10
    太å¤ļçļĦ
    -0.09
    强硬
    -0.09
    ABCDEFG
    -0.09
    rote
    -0.09
    á»Ŀ
    -0.08
    为主çļĦ
    -0.08
    ëŀı
    -0.08
    å¹¿æ³ĽçļĦ
    -0.08
    -centric
    -0.08
    POSITIVE LOGITS
    åĮħ袱
    0.09
    à¸Ľà¸£à¸°à¸Īำ
    0.08
    ä¸ĢæľŁ
    0.08
     whit
    0.08
     Kur
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    çĽĹ
    0.08
    æŃ£å¼ı
    0.08
    wh
    0.08
    æĪĸå¤ļ
    0.08
    Activations Density 0.126%

    No Known Activations