© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16755
    Prev
    Next
    INDEX
    Explanations

    `v.` or `v.` followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鼼
    -0.07
    äºĨæī¿
    -0.07
    æĭħä¿Ŀé£İéĻ©
    -0.07
     geler
    -0.07
     EMPRES
    -0.06
     secretaria
    -0.06
    好象
    -0.06
    alagi
    -0.06
    æ´ŀ
    -0.06
    ãģ¯ãģĦãģĭãģĮ
    -0.06
    POSITIVE LOGITS
    ,
    0.06
    éĺ»
    0.06
    éĹ´æİ¥
    0.06
     v
    0.05
     ex
    0.05
    0.05
    ç´¢
    0.05
    .
    0.05
    ÑģÑĤи
    0.05
    catch
    0.05
    Activations Density 0.837%

    No Known Activations