© 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. 30276
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    çĭ±
    -0.09
    佩
    -0.09
    ลำ
    -0.09
    éĢIJä¸Ģ
    -0.09
    çı
    -0.09
    ÑĤок
    -0.09
    å¤ļå¤ļ
    -0.09
    éĢIJ
    -0.09
    ä¸¥æł¼çļĦ
    -0.09
    åĴ±ä»¬
    -0.09
    POSITIVE LOGITS
    ä¼ij
    0.10
    鸾
    0.10
     ket
    0.10
    urette
    0.09
    ãģĦãģĭ
    0.09
    åIJĦç±»
    0.08
    æ»ŀåIJİ
    0.08
     благод
    0.08
    个人è§ĤçĤ¹
    0.08
    bro
    0.08
    Activations Density 0.001%

    No Known Activations