© 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. 16818
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas of the form variable = expression

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ikk
    -0.06
    izzy
    -0.05
    ç«Ł
    -0.05
    以德
    -0.05
    è§ĦåĪĴåĴĮ
    -0.05
    chrift
    -0.05
    åľ¨ä¸Ģ
    -0.05
    lak
    -0.05
    izz
    -0.05
    addresses
    -0.05
    POSITIVE LOGITS
    å½¹
    0.05
     orderly
    0.05
    åįĸ
    0.05
    æĬ¢
    0.05
    æĸĩ稿
    0.05
    #=
    0.05
    ç¦ı
    0.05
    #/
    0.05
     Gos
    0.05
    eps
    0.05
    Activations Density 0.009%

    No Known Activations